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

    Neuronpedia

    INDEX
    Explanations

    /

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (fileName
    -0.07
    -commercial
    -0.07
     vydání
    -0.07
    Number
    -0.06
     наступ
    -0.06
     цель
    -0.06
    _OC
    -0.06
    _PUR
    -0.06
     Hoa
    -0.06
     mortality
    -0.06
    POSITIVE LOGITS
    .removeChild
    0.07
    /autoload
    0.06
     공부
    0.06
    ing
    0.06
     wishing
    0.06
    ثل
    0.06
     자동
    0.06
    妹
    0.06
     Ради
    0.06
     concerning
    0.06
    Act Density 0.006%

    No Known Activations