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

    Neuronpedia

    INDEX
    Explanations

    theorem

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    بيع
    -0.08
     outreach
    -0.08
     Vertrieb
    -0.08
     intellectually
    -0.08
     emotionally
    -0.07
     monoton
    -0.07
     temperatures
    -0.07
     lecture
    -0.07
     vendas
    -0.07
     temperature
    -0.07
    POSITIVE LOGITS
     gcd
    0.09
    积分
    0.08
    with
    0.08
    _DEF
    0.07
     controlar
    0.07
     kruiden
    0.07
    成立
    0.07
     weighed
    0.07
     ratios
    0.07
    hol
    0.07
    Act Density 0.003%

    No Known Activations