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

    Neuronpedia

    INDEX
    Explanations

    header

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    企
    -0.07
    TextBox
    -0.07
     tabs
    -0.06
    .LOC
    -0.06
    Reality
    -0.06
    	Button
    -0.06
    вич
    -0.06
    checkbox
    -0.06
     Лени
    -0.06
    师
    -0.06
    POSITIVE LOGITS
    _rating
    0.07
     č
    0.06
    /host
    0.06
     deg
    0.06
    acağ
    0.06
     Hartford
    0.06
     Skate
    0.06
    .coord
    0.06
    였
    0.06
     프랑스
    0.06
    Act Density 0.004%

    No Known Activations