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

    Neuronpedia

    INDEX
    Explanations

    phrases or expressions related to making bets or expressing confidence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    betting and predicting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Clearly
    -0.42
    Largo
    -0.41
    EIF
    -0.41
    Gest
    -0.39
    esModule
    -0.39
    Marcia
    -0.39
    quité
    -0.39
    緒
    -0.39
     geheel
    -0.39
     separat
    -0.39
    POSITIVE LOGITS
    HtmlAttribute
    0.55
     protoimpl
    0.54
     bet
    0.53
    httphttps
    0.52
    bitField
    0.52
     bets
    0.50
     للمعارف
    0.49
    RTLU
    0.48
     estekak
    0.46
    ⤒
    0.46
    Act Density 0.004%

    No Known Activations