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

    Neuronpedia

    INDEX
    Explanations

    was or were

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     implied
    -0.07
    included
    -0.07
    싼
    -0.07
    лас
    -0.07
    Spl
    -0.07
     Composer
    -0.07
    confirm
    -0.07
     conduc
    -0.07
    ulpt
    -0.06
    shown
    -0.06
    POSITIVE LOGITS
     //
↵
↵
    0.08
     Rockefeller
    0.08
     מדה
    0.07
    提现
    0.07
    太平
    0.07
    柏林
    0.07
    🌬
    0.07
    专业化
    0.07
    五月
    0.07
     הדבר
    0.07
    Act Density 0.130%

    No Known Activations