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

    Neuronpedia

    INDEX
    Explanations

    Building and Development

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     paix
    -0.08
    _accept
    -0.07
     नंबर
    -0.07
     licenci
    -0.07
    Hire
    -0.07
     ni
    -0.07
     interplay
    -0.07
     ارت
    -0.07
     lec
    -0.07
     sla
    -0.07
    POSITIVE LOGITS
     opposed
    0.08
    ű
    0.08
     aplicado
    0.08
    大量
    0.08
     Applies
    0.08
    扫
    0.08
     основ
    0.07
     бутыл
    0.07
    方式
    0.07
    ，非常
    0.07
    Act Density 0.344%

    No Known Activations