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

    Neuronpedia

    INDEX
    Explanations

    legality harm help

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     innumerable
    0.96
    <unused1004>
    0.94
    ៨
    0.93
    ៧
    0.93
    ۲
    0.92
     Because
    0.91
     médiocrement
    0.89
    សំ
    0.89
    ೬
    0.89
     remarkably
    0.88
    POSITIVE LOGITS
    1.41
    :
    0.98
    ↵
    0.84
    ...
    0.83
    ,...
    0.82
    ↵↵↵
    0.80
    <0x0D>
    0.80
    ,
    0.79
    </h2>
    0.76
    .
    0.76
    Act Density 0.363%

    No Known Activations