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

    Neuronpedia

    INDEX
    Explanations

    convenience

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    チーム
    -0.08
    ruc
    -0.07
    auc
    -0.07
    .ch
    -0.07
    信貸
    -0.07
    slashes
    -0.07
     tịch
    -0.07
     cloves
    -0.06
    ตรวจ
    -0.06
     retVal
    -0.06
    POSITIVE LOGITS
     النف
    0.08
     perk
    0.07
     '',
    0.07
     diversos
    0.07
     diversas
    0.07
    基因
    0.07
     Rise
    0.07
    variably
    0.07
    ива
    0.06
    );\↵
    0.06
    Act Density 0.015%

    No Known Activations