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

    Neuronpedia

    INDEX
    Explanations

    foreign language phrases

    np_acts-logits-general · gemini-2.5-flash-lite

    ## response intro

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     to
    0.75
     of
    0.68
     with
    0.52
     at
    0.49
    ătoare
    0.49
     from
    0.47
     permukaan
    0.46
     tại
    0.46
     that
    0.46
     của
    0.46
    POSITIVE LOGITS
    و
    0.76
    ↵
    0.70
    ل
    0.66
    ის
    0.59
    л
    0.58
    op
    0.56
    ко
    0.56
    ле
    0.56
    ט
    0.56
    他的
    0.55
    Act Density 3.566%

    No Known Activations