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

    Neuronpedia

    INDEX
    Explanations

    01

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Perr
    -0.08
     tə
    -0.08
    UIColor
    -0.08
     соверш
    -0.08
     misch
    -0.07
     प्रेस
    -0.07
    presas
    -0.07
    ぱ
    -0.07
     இற
    -0.07
    pres
    -0.07
    POSITIVE LOGITS
     tenancy
    0.08
    要求
    0.08
    Compliance
    0.08
    (timeout
    0.08
     certification
    0.08
     ان
    0.07
     кел
    0.07
     compliance
    0.07
     Flood
    0.07
     Compliance
    0.07
    Act Density 0.003%

    No Known Activations