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

    Neuronpedia

    INDEX
    Explanations

    Transistor circuits

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    иру
    -0.07
     Ere
    -0.07
     Drama
    -0.07
    ItemType
    -0.06
     heraus
    -0.06
     dose
    -0.06
     },↵↵↵
    -0.06
    dre
    -0.06
     місто
    -0.06
     monsters
    -0.06
    POSITIVE LOGITS
     为
    0.07
    =l
    0.06
    �
    0.06
     policymakers
    0.06
    _numeric
    0.06
     분
    0.06
    ΣΤ
    0.06
    getC
    0.06
     isValid
    0.06
     h
    0.06
    Act Density 0.038%

    No Known Activations