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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    声道
    -0.07
     prosecutors
    -0.07
    恺
    -0.07
    腒
    -0.07
     exem
    -0.07
     &&
    -0.06
    REM
    -0.06
     Fitzgerald
    -0.06
    /arm
    -0.06
     reports
    -0.06
    POSITIVE LOGITS
    蓝色
    0.08
     mogła
    0.07
    золот
    0.07
     ml
    0.07
     kettle
    0.07
    ISED
    0.07
    🐑
    0.07
     ObjectOutputStream
    0.07
     بالت
    0.07
    的责任
    0.06
    Act Density 0.029%

    No Known Activations