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

    Neuronpedia

    INDEX
    Explanations

    pone

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     国家
    -0.06
    <
    -0.06
    ाद
    -0.06
     exemplary
    -0.06
     employ
    -0.05
    area
    -0.05
     objekt
    -0.05
    inst
    -0.05
    grey
    -0.05
     маг
    -0.05
    POSITIVE LOGITS
     Placement
    0.09
    pone
    0.08
     poisoning
    0.07
    ستانی
    0.07
     Candle
    0.07
     Benton
    0.07
     ''){↵
    0.07
    _mouse
    0.07
    nin
    0.07
    INATION
    0.07
    Act Density 0.003%

    No Known Activations