Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    references to scientific or medical analysis processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Preceding percentages, parentheses, or certain function words

    np_acts-logits-general · gemini-2.0-flash

    automatic analyzers, formaldehyde, latex, license

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     saites
    -0.64
     beginnetje
    -0.63
    MENAFN
    -0.63
     שוליים
    -0.61
    doGet
    -0.57
    GEBURTSDATUM
    -0.57
    setVerticalGroup
    -0.56
    providedIn
    -0.56
    AccessFile
    -0.54
     Quince
    -0.54
    POSITIVE LOGITS
    ↵↵↵↵↵↵↵↵↵
    0.64
     resourceCulture
    0.56
    ↵↵↵↵↵↵
    0.54
    </code>
    0.49
    ↵↵↵↵↵
    0.47
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.47
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.46
    ↵↵↵↵↵↵↵↵↵↵↵↵
    0.46
    ↵↵↵↵↵↵↵↵
    0.46
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.46
    Act Density 0.127%

    No Known Activations