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

    Neuronpedia

    INDEX
    Explanations

    person

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     kinetics
    -0.06
     observations
    -0.06
    enant
    -0.06
    _make
    -0.06
    _cells
    -0.06
     growers
    -0.06
     adaptations
    -0.06
     parked
    -0.06
     LZ
    -0.06
     pozdě
    -0.06
    POSITIVE LOGITS
    лач
    0.07
    expense
    0.07
    FormatException
    0.07
    ResourceId
    0.07
    untas
    0.07
     Rocks
    0.07
    ��
    0.07
    cot
    0.06
    .Ret
    0.06
     Trudeau
    0.06
    Act Density 0.004%

    No Known Activations