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

    Neuronpedia

    INDEX
    Explanations

    code/data delimiters

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .AttributeSet
    -0.06
    basic
    -0.06
     ADD
    -0.06
    anggal
    -0.06
     nakne
    -0.06
    ters
    -0.06
    /fontawesome
    -0.06
    objects
    -0.06
     anderen
    -0.06
     ngoài
    -0.06
    POSITIVE LOGITS
    DDevice
    0.07
    _numer
    0.06
     Law
    0.06
    _games
    0.06
     sulf
    0.06
    orque
    0.06
    .getNumber
    0.06
    """
↵
↵
    0.06
    ライト
    0.06
    erca
    0.06
    Act Density 0.012%

    No Known Activations