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

    Neuronpedia

    INDEX
    Explanations

    solving steps or simplify

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     manj
    0.87
     drawable
    0.86
    dokkaHtml
    0.85
    Таким
    0.85
    iliśmy
    0.84
     tehát
    0.83
     sesuatu
    0.82
     좋습니다
    0.81
     सौंद
    0.80
     sicuramente
    0.80
    POSITIVE LOGITS
    ת
    0.84
    renched
    0.79
    濘
    0.78
    reet
    0.75
     последних
    0.73
     prejudice
    0.73
    ная
    0.72
     fuer
    0.71
    raron
    0.71
    вшая
    0.71
    Act Density 0.000%

    No Known Activations