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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    благо
    -0.07
    одерж
    -0.07
    �
    -0.06
    @author
    -0.06
    不甘
    -0.06
    שפע
    -0.06
    穟
    -0.06
    ﺧ
    -0.06
     puzzles
    -0.06
    �
    -0.06
    POSITIVE LOGITS
    (da
    0.09
    .TableName
    0.08
    (-
    0.08
    (xhr
    0.07
    (false
    0.07
    _histogram
    0.07
    romium
    0.07
    雪花
    0.07
    (userid
    0.07
    arrow
    0.07
    Act Density 0.013%

    No Known Activations