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

    Neuronpedia

    INDEX
    Explanations

    statistical significance

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     HID
    -0.10
     deporte
    -0.09
     eyew
    -0.08
     воспри
    -0.08
     limitless
    -0.08
     xog
    -0.08
     रोग
    -0.07
     Bose
    -0.07
    osomes
    -0.07
     sports
    -0.07
    POSITIVE LOGITS
    _Module
    0.08
     predicting
    0.08
    (Direction
    0.08
    税
    0.08
    宇
    0.08
     statutory
    0.08
    unicode
    0.07
     prosecute
    0.07
    <<"\
    0.07
     thân
    0.07
    Act Density 0.003%

    No Known Activations