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

    Neuronpedia

    INDEX
    Explanations

    equations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	scale
    -0.07
    .rabbit
    -0.07
    ذي
    -0.06
     Dos
    -0.06
    的事情
    -0.06
     RMS
    -0.06
     gown
    -0.06
     ทอง
    -0.06
    paste
    -0.06
     бел
    -0.06
    POSITIVE LOGITS
    购
    0.07
    문제
    0.07
    �i
    0.06
    *S
    0.06
     prázd
    0.06
    )&&(
    0.06
    ewis
    0.06
    UniformLocation
    0.06
     spaces
    0.06
    QE
    0.06
    Act Density 0.024%

    No Known Activations