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

    Neuronpedia

    INDEX
    Explanations

    punishment

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _curve
    -0.06
    ango
    -0.06
    рам
    -0.06
    695
    -0.06
     mafia
    -0.06
    罗
    -0.06
    rite
    -0.06
    ICAST
    -0.06
     Cars
    -0.06
    	client
    -0.06
    POSITIVE LOGITS
     hiss
    0.06
    祝
    0.06
    .estado
    0.06
     getPosition
    0.06
    .mContext
    0.06
     mejorar
    0.06
     FY
    0.06
    -common
    0.06
    -count
    0.06
    _study
    0.06
    Act Density 0.002%

    No Known Activations