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

    Neuronpedia

    INDEX
    Explanations

    ty

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Swansea
    -0.06
     paramMap
    -0.06
     expenditures
    -0.06
    <Button
    -0.06
    *(-
    -0.06
     developments
    -0.06
    _VERIFY
    -0.06
    =[]↵
    -0.06
    _glyph
    -0.06
    classify
    -0.06
    POSITIVE LOGITS
    δρα
    0.07
    pill
    0.07
     distracted
    0.07
    рив
    0.07
    -next
    0.06
    χι
    0.06
    .out
    0.06
    csrf
    0.06
    лами
    0.06
     플레이
    0.06
    Act Density 0.002%

    No Known Activations