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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    970
    -0.07
     footsteps
    -0.07
    .plot
    -0.06
    ูช
    -0.06
    ết
    -0.06
     张
    -0.06
    лемент
    -0.06
     Governments
    -0.06
    Vintage
    -0.06
    Mine
    -0.06
    POSITIVE LOGITS
    setUp
    0.07
    kých
    0.06
    (Vector
    0.06
     समस
    0.06
    .angular
    0.06
    ие
    0.06
    atial
    0.05
     počtu
    0.05
     свя
    0.05
    .Wait
    0.05
    Act Density 0.157%

    No Known Activations