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
    ्कर
    -0.07
    긴
    -0.07
    번
    -0.07
    垂
    -0.07
     Indices
    -0.07
    rav
    -0.07
     substitutions
    -0.07
    iu
    -0.07
    _KEYWORD
    -0.07
    ыш
    -0.07
    POSITIVE LOGITS
    .bs
    0.07
    Also
    0.06
     ποι
    0.06
     nhận
    0.06
    "){↵
    0.06
    .rad
    0.06
    (Global
    0.06
     ALSO
    0.06
     �
    0.06
    :".
    0.06
    Act Density 0.013%

    No Known Activations