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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     refusing
    -0.08
     blessing
    -0.07
     longitud
    -0.07
     spons
    -0.07
     FedEx
    -0.06
     fasta
    -0.06
     suspicion
    -0.06
    YYY
    -0.06
     forg
    -0.06
     jurisdiction
    -0.06
    POSITIVE LOGITS
     recre
    0.06
    ))-
    0.06
    ısız
    0.06
     Š
    0.06
    .InnerException
    0.06
    DownList
    0.06
    主义
    0.06
     ≠
    0.06
    =l
    0.06
    brıs
    0.06
    Act Density 0.127%

    No Known Activations