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

    Neuronpedia

    INDEX
    Explanations

    negative sentiment

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     хто
    -0.07
     Pixels
    -0.06
    ْف
    -0.06
    roph
    -0.06
    stones
    -0.06
    jack
    -0.06
     basal
    -0.06
    zc
    -0.06
     enh
    -0.06
     fetus
    -0.06
    POSITIVE LOGITS
    >{@
    0.07
    .bean
    0.07
    Les
    0.07
     filed
    0.06
     HT
    0.06
    Des
    0.06
     "{
    0.06
     FString
    0.06
    British
    0.06
    bool
    0.06
    Act Density 0.046%

    No Known Activations