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

    Neuronpedia

    INDEX
    Explanations

    As a model

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ().
    0.74
     ().
    0.73
     тоже
    0.71
     _)
    0.68
    ）.
    0.66
    。)
    0.65
     채
    0.65
    _.
    0.63
    $.\
    0.62
    .).
    0.62
    POSITIVE LOGITS
    sembled
    1.14
    sembling
    1.03
     you
    0.95
     mentioned
    0.88
     with
    0.87
    يك
    0.86
    en
    0.85
    ي
    0.84
     With
    0.83
    i
    0.83
    Act Density 0.016%

    No Known Activations