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

    Neuronpedia

    INDEX
    Explanations

    in or an the phone kids experts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    bery
    0.76
    への
    0.76
     sembra
    0.75
    gesetz
    0.73
    ab
    0.71
    angkap
    0.71
     būti
    0.71
     migli
    0.70
     Auswahl
    0.70
    shoz
    0.70
    POSITIVE LOGITS
    ים
    0.83
     o
    0.79
    те
    0.78
    ี
    0.77
    тени
    0.76
    н
    0.75
     summit
    0.71
     wickets
    0.71
     woo
    0.69
    닌
    0.68
    Act Density 0.000%

    No Known Activations