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

    Neuronpedia

    INDEX
    Explanations

    error or cannot calculate

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    тім
    0.69
    ،
    0.67
    *,
    0.66
    ows
    0.63
     як
    0.63
    Committee
    0.63
    ني
    0.63
    أن
    0.63
    helps
    0.63
    )،
    0.62
    POSITIVE LOGITS
     nedostat
    0.61
    तया
    0.61
     hamstring
    0.60
    ಿಂದ
    0.58
     worse
    0.57
     kenapa
    0.57
     worst
    0.57
     comercial
    0.57
    ！
    0.57
     [%
    0.57
    Act Density 0.609%

    No Known Activations