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

    Neuronpedia

    INDEX
    Explanations

    AI instructions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    et
    0.40
    olut
    0.37
    ulint
    0.37
    n
    0.37
    hor
    0.37
    yya
    0.36
    esign
    0.36
     ，
    0.36
    etl
    0.36
    ны
    0.34
    POSITIVE LOGITS
    ہ
    0.57
    ൻ
    0.46
    도
    0.43
    ق
    0.42
    ید
    0.41
     prochain
    0.40
    Y
    0.40
     humains
    0.39
     моём
    0.39
     mois
    0.39
    Act Density 0.000%

    No Known Activations