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

    Neuronpedia

    INDEX
    Explanations

    other

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     nl
    -0.07
    ा-
    -0.07
    .Getter
    -0.06
    Director
    -0.06
     crises
    -0.06
     motorists
    -0.06
     सव
    -0.06
     Liberty
    -0.06
    .locals
    -0.06
     Gil
    -0.06
    POSITIVE LOGITS
    .train
    0.06
    <j
    0.06
    uição
    0.06
    桃
    0.06
     unknown
    0.06
    _typeDefinition
    0.06
    research
    0.06
     vowed
    0.06
    won
    0.06
     Investig
    0.06
    Act Density 0.043%

    No Known Activations