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

    Neuronpedia

    INDEX
    Explanations

    references to control and dominance within societal structures

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

    small number

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     wireType
    -0.65
    withIdentifier
    -0.49
    aarrggbb
    -0.45
    thâu
    -0.45
    новниш
    -0.44
     resourceCulture
    -0.43
     Numerade
    -0.43
    تقاوى
    -0.42
    Попис
    -0.42
    Hozzáférés
    -0.41
    POSITIVE LOGITS
     few
    1.99
    few
    1.74
    Few
    1.73
     Few
    1.63
     wenigen
    1.56
     wenige
    1.51
     fewer
    1.51
     handful
    1.48
     pochi
    1.48
     pocos
    1.44
    Act Density 0.238%

    No Known Activations