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

    Neuronpedia

    INDEX
    Explanations

    a

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     prison
    -0.07
     Id
    -0.06
     předmět
    -0.06
    重新
    -0.06
     SIDE
    -0.06
     तम
    -0.06
    Unlock
    -0.06
     uneasy
    -0.06
     Ін
    -0.06
    -grid
    -0.06
    POSITIVE LOGITS
     eventType
    0.07
     filing
    0.06
    ITA
    0.06
    �
    0.06
    lan
    0.06
    gang
    0.06
    خصوص
    0.06
    712
    0.06
     Helvetica
    0.06
    터
    0.06
    Act Density 0.000%

    No Known Activations