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
    742
    -0.07
     rozhodnutí
    -0.06
    390
    -0.06
    _operations
    -0.06
    يه
    -0.06
     Бол
    -0.06
    �
    -0.06
     finde
    -0.06
     indifference
    -0.06
    一度
    -0.06
    POSITIVE LOGITS
    ccd
    0.06
    .Validate
    0.06
    *******
↵
    0.06
    _Current
    0.06
    เขา
    0.06
    реш
    0.06
    명
    0.06
    στε
    0.06
     """
↵
    0.06
    isclosed
    0.06
    Act Density 0.002%

    No Known Activations