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

    Neuronpedia

    INDEX
    Explanations

    Cards and values

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     stimulates
    -0.08
    _here
    -0.07
    -bound
    -0.07
     לעבוד
    -0.07
     מוצר
    -0.07
    巡视
    -0.07
    nte
    -0.07
     cooperative
    -0.07
     Penny
    -0.06
    */),
    -0.06
    POSITIVE LOGITS
    Jason
    0.08
    ▷
    0.06
    Transmission
    0.06
    锖
    0.06
    痛
    0.06
    edian
    0.06
    手機
    0.06
    rk
    0.06
    ------------------------------------------------------------------------------------------------
    0.06
    رابط
    0.06
    Act Density 0.011%

    No Known Activations