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

    Neuronpedia

    INDEX
    Explanations

    .

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     وزن
    -0.07
     пар
    -0.07
     instruction
    -0.06
     exams
    -0.06
     lao
    -0.06
    _INFORMATION
    -0.06
     شکست
    -0.06
    _rights
    -0.06
     collapsed
    -0.06
    iguous
    -0.06
    POSITIVE LOGITS
     Which
    0.07
     SqlConnection
    0.07
    iling
    0.07
    .LoggerFactory
    0.07
     Ellie
    0.06
     audi
    0.06
    inant
    0.06
    CallableWrapper
    0.06
     Theo
    0.06
     Hogwarts
    0.06
    Act Density 0.000%

    No Known Activations