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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating familiarity or knowledge regarding a subject

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

    degree of knowing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AutoScaleMode
    -0.77
    SharedDtor
    -0.65
     HasFactory
    -0.60
    Personendaten
    -0.60
     EconPapers
    -0.58
    __":
    -0.58
    postIndex
    -0.57
    //
    -0.56
    IntoConstraints
    -0.56
     متعلقه
    -0.55
    POSITIVE LOGITS
     familiar
    0.48
     mengenal
    0.42
     familiarity
    0.41
    よく
    0.40
    znám
    0.40
     kennt
    0.39
    をよく
    0.39
     conoscenza
    0.37
    Familiar
    0.37
    fid
    0.37
    Act Density 0.022%

    No Known Activations