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

    Neuronpedia

    INDEX
    Explanations

    choice, select, choose

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    INV
    0.40
    Ko
    0.39
    Ass
    0.38
    શી
    0.37
    INS
    0.35
    WidgetItem
    0.35
    Led
    0.35
    Worked
    0.35
    Wallet
    0.34
    Os
    0.34
    POSITIVE LOGITS
     作为
    0.50
     jako
    0.50
    作为
    0.47
    으로서
    0.46
     sifatida
    0.45
     Sebagai
    0.45
    としても
    0.44
     interracial
    0.44
    作為
    0.43
    로서
    0.41
    Act Density 0.002%

    No Known Activations