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

    Neuronpedia

    INDEX
    Explanations

    strings of characters that appear to be identifiers

    oai_token-act-pair · gemini-2.0-flash

    non-English or code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ſelf
    -0.46
    нє
    -0.39
     Monfieur
    -0.39
     Fides
    -0.36
     itſelf
    -0.36
    mota
    -0.35
     Efq
    -0.35
    ofluorescence
    -0.32
     myſelf
    -0.31
    ખ
    -0.31
    POSITIVE LOGITS
    WebVitals
    0.88
    PYX
    0.78
    الإنجليزية
    0.75
    onOptions
    0.70
     onCancelled
    0.69
     Audiodateien
    0.69
     protoimpl
    0.69
    بوابة
    0.69
     للاسماء
    0.68
    bootstrapcdn
    0.67
    Act Density 6.896%

    No Known Activations