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

    Neuronpedia

    INDEX
    Explanations

    numerical values and mathematical operators

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

    Mathematical expressions and negative numbers

    np_acts-logits-general · gemini-2.0-flash

    code punctuation and digits after "1"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    iveau
    -0.64
    ★★★★★
    -0.56
     Vat
    -0.55
    aarrggbb
    -0.54
    AsUp
    -0.53
    لار
    -0.53
    setVerticalGroup
    -0.50
    Syllabus
    -0.50
     VIDEOTAPE
    -0.50
    Vat
    -0.49
    POSITIVE LOGITS
    protoimpl
    0.58
    EndInit
    0.57
    Autoritní
    0.52
     <=",
    0.51
    findpost
    0.51
     []:
    0.50
    انه
    0.49
     Савезне
    0.49
     cherchés
    0.49
    ViewFeatures
    0.48
    Act Density 0.880%

    No Known Activations