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

    Neuronpedia

    INDEX
    Explanations

    add new

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    EMALE
    -0.07
    Perhaps
    -0.07
    makes
    -0.07
     societies
    -0.06
     pancakes
    -0.06
     picking
    -0.06
    _people
    -0.06
    attended
    -0.06
     seized
    -0.06
    affle
    -0.06
    POSITIVE LOGITS
    を作
    0.07
    /*================================================================
    0.07
    獲得
    0.06
     impover
    0.06
    _env
    0.06
     مرتبط
    0.06
     leaps
    0.06
     яр
    0.06
    ีฬา
    0.06
     hangs
    0.06
    Act Density 0.019%

    No Known Activations