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

    Neuronpedia

    INDEX
    Explanations

    points

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    tmp
    -0.07
    .{
    -0.06
     meddling
    -0.06
    .pix
    -0.06
     ввод
    -0.06
    ,str
    -0.06
    _daily
    -0.06
    obraz
    -0.06
    Evaluate
    -0.06
     convers
    -0.06
    POSITIVE LOGITS
    [A
    0.07
    Sit
    0.07
    .getType
    0.07
     Committee
    0.07
     Wife
    0.07
    conomics
    0.06
     instability
    0.06
     moment
    0.06
     Sit
    0.06
     После
    0.06
    Act Density 0.016%

    No Known Activations