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

    Neuronpedia

    INDEX
    Explanations

    terms related to data detection and analysis in various contexts

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

    analysis, detection, approvals, catalysts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Zwiebel
    -0.65
     Geist
    -0.59
    <bos>
    -0.58
     Ressource
    -0.57
    tance
    -0.56
     Mangel
    -0.56
     Pritchard
    -0.56
     Verband
    -0.56
     Schatz
    -0.56
    alisation
    -0.56
    POSITIVE LOGITS
     wuß
    0.58
     meisjes
    0.58
    ésult
    0.56
     verantwoorde
    0.54
    étoit
    0.53
     zijne
    0.52
     ioutil
    0.50
     werkzaam
    0.50
    🏻
    0.49
    (/\
    0.49
    Act Density 0.222%

    No Known Activations