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
     Coupe
    -0.07
     dk
    -0.07
    %"↵
    -0.06
    that
    -0.06
    ,c
    -0.06
    regon
    -0.06
    chartInstance
    -0.06
     christian
    -0.06
    真爱
    -0.06
     nationalists
    -0.06
    POSITIVE LOGITS
    蚤
    0.07
    老师
    0.07
    otre
    0.07
    .Rect
    0.07
    FlatButton
    0.07
    _CAL
    0.07
    _latitude
    0.07
    .Selected
    0.07
     Offline
    0.07
    ecided
    0.07
    Act Density 0.015%

    No Known Activations