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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ock
    -0.07
    _sc
    -0.07
    ological
    -0.07
    heat
    -0.07
    '];
↵
↵
    -0.07
    锻
    -0.07
    .asarray
    -0.06
    铎
    -0.06
    sea
    -0.06
     travelled
    -0.06
    POSITIVE LOGITS
     günd
    0.08
    /windows
    0.08
     klik
    0.08
     favicon
    0.07
    Margins
    0.07
     당신
    0.07
    .todo
    0.07
     luggage
    0.07
     portfolios
    0.07
     KC
    0.07
    Act Density 0.059%

    No Known Activations