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

    Neuronpedia

    INDEX
    Explanations

    /javascript

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     lifting
    -0.06
    _tl
    -0.06
     全
    -0.06
     produ
    -0.06
    resize
    -0.06
    [left
    -0.06
     xl
    -0.05
    _pen
    -0.05
    .operations
    -0.05
     Bolivia
    -0.05
    POSITIVE LOGITS
    さま
    0.07
     Budget
    0.06
     Česko
    0.06
    師
    0.06
    вердж
    0.06
    _SUCCESS
    0.06
    ycler
    0.06
     благод
    0.06
    each
    0.06
    atoire
    0.06
    Act Density 0.002%

    No Known Activations