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

    Neuronpedia

    INDEX
    Explanations

    section headers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     messes
    0.61
    qualiter
    0.59
    物が
    0.59
    원이
    0.58
     ძალიან
    0.57
     деву
    0.56
     مبنی
    0.56
    회가
    0.55
     כמו
    0.55
    이지만
    0.55
    POSITIVE LOGITS
    نا
    0.60
    ad
    0.57
    end
    0.55
     plaintiff
    0.52
    ah
    0.50
    eng
    0.50
    న్
    0.50
    ون
    0.49
    ä
    0.47
    as
    0.47
    Act Density 0.050%

    No Known Activations