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

    Neuronpedia

    INDEX
    Explanations

    firmware

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     přib
    -0.07
    romě
    -0.07
     rawData
    -0.07
    .vertex
    -0.07
    $username
    -0.06
    .search
    -0.06
    .",
    -0.06
    никами
    -0.06
    t
    -0.06
    chers
    -0.06
    POSITIVE LOGITS
    .vo
    0.07
     Получ
    0.07
    غم
    0.07
    part
    0.06
    取得
    0.06
    �
    0.06
    ENCH
    0.06
    ,\↵
    0.06
     pruning
    0.06
    fried
    0.06
    Act Density 0.003%

    No Known Activations