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

    Neuronpedia

    INDEX
    Explanations

    personal names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ◻
    0.56
    (
    0.56
    dataframe
    0.55
    **
    0.55
    ул
    0.54
    filesystem
    0.54
    quad
    0.54
    보다
    0.54
    config
    0.54
    (_
    0.53
    POSITIVE LOGITS
     himself
    0.97
     Arzt
    0.87
     Urban
    0.86
    老师
    0.85
     তাঁর
    0.85
     spielte
    0.85
     Robert
    0.84
     સંપૂર્ણ
    0.84
    老師
    0.83
     aveva
    0.82
    Act Density 0.122%

    No Known Activations