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

    Neuronpedia

    INDEX
    Explanations

    dissecting code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     IncludeField
    0.93
     પટેલ
    0.87
    isten
    0.81
    тивно
    0.81
    Mobs
    0.80
    LEN
    0.78
    idegg
    0.78
    ревно
    0.77
    asi
    0.76
    ao
    0.75
    POSITIVE LOGITS
     yolks
    0.83
    )"
    0.81
     anuv
    0.80
     перемо
    0.79
    ﻭ
    0.78
     vibhav
    0.78
     воды
    0.77
     vody
    0.77
    sah
    0.76
     interdit
    0.76
    Act Density 0.000%

    No Known Activations