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

    Neuronpedia

    INDEX
    Explanations

    sorting algorithms

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ContextMenu
    -0.07
     Cham
    -0.07
    创新能力
    -0.07
    צא
    -0.07
    当事人
    -0.07
     Closet
    -0.07
    UNUSED
    -0.07
     outfit
    -0.06
    收受
    -0.06
     silk
    -0.06
    POSITIVE LOGITS
    老化
    0.08
     sergeant
    0.08
     serge
    0.07
    $input
    0.07
     Rising
    0.07
    аз
    0.07
    漏水
    0.07
     permite
    0.07
    .fil
    0.07
    个赛季
    0.07
    Act Density 0.005%

    No Known Activations