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

    Neuronpedia

    INDEX
    Explanations

    code and math

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ework
    -0.07
    those
    -0.07
     등의
    -0.06
     Тут
    -0.06
    .objects
    -0.06
    las
    -0.06
     doGet
    -0.06
    _capacity
    -0.06
    246
    -0.06
    ла
    -0.06
    POSITIVE LOGITS
    Spell
    0.07
     Toll
    0.07
    ี,
    0.07
    IGNORE
    0.07
    HeaderView
    0.07
    :expr
    0.06
     harvesting
    0.06
    HERE
    0.06
     —
    0.06
    ('%
    0.06
    Act Density 0.000%

    No Known Activations