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

    Neuronpedia

    INDEX
    Explanations

    units

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Automatically
    -0.07
    .XPath
    -0.07
    杯
    -0.06
     хвор
    -0.06
    _tree
    -0.06
     >/
    -0.06
    HttpPost
    -0.06
    IColor
    -0.06
    NewUrlParser
    -0.06
     capac
    -0.06
    POSITIVE LOGITS
    mov
    0.07
    ieber
    0.06
    %c
    0.06
    üs
    0.06
     skies
    0.06
    地说
    0.06
     strokes
    0.06
     tweaking
    0.06
    ší
    0.06
     bearer
    0.06
    Act Density 0.025%

    No Known Activations