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

    Neuronpedia

    INDEX
    Explanations

    titles like Prof. or Dr

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    5
    0.80
    g
    0.79
    ↵↵
    0.77
    ↵
    0.76
    er
    0.75
    '
    0.72
    S
    0.72
    4
    0.68
    را
    0.66
    ५
    0.66
    POSITIVE LOGITS
    郆
    0.79
    畞
    0.71
     be
    0.69
    كان
    0.69
    欴
    0.69
    䧣
    0.67
    䟝
    0.66
    㝢
    0.66
     et
    0.64
    ką
    0.64
    Act Density 0.002%

    No Known Activations