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

    Neuronpedia

    INDEX
    Explanations

    math exercises and quizzes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     notes
    0.41
    RON
    0.41
     trag
    0.37
     acc
    0.37
     way
    0.37
    eb
    0.36
    ედ
    0.36
     genetic
    0.36
     duties
    0.36
    ارب
    0.36
    POSITIVE LOGITS
     оригина
    0.50
     utile
    0.46
    Traité
    0.46
     useful
    0.46
     originals
    0.43
     útil
    0.43
    utilise
    0.43
     original
    0.42
    是个
    0.42
     Original
    0.42
    Act Density 0.000%

    No Known Activations