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

    Neuronpedia

    INDEX
    Explanations

    code configurations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     discrepan
    -0.07
     StringBuffer
    -0.07
    芄
    -0.07
     Forrest
    -0.07
     Alibaba
    -0.06
     Pett
    -0.06
    食堂
    -0.06
     discussed
    -0.06
    améliorer
    -0.06
    far
    -0.06
    POSITIVE LOGITS
    ...)↵
    0.08
    용
    0.07
     LIKE
    0.07
    scaling
    0.07
    對方
    0.06
    +E
    0.06
    .addObject
    0.06
    -nine
    0.06
    天
    0.06
     ++;↵
    0.06
    Act Density 0.256%

    No Known Activations