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

    Neuronpedia

    INDEX
    Explanations

    phrases or constructs involving numerical quantities or amounts

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

    number of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    󠁢
    -0.40
    poxy
    -0.40
    dial
    -0.39
     חיצוניים
    -0.38
     LW
    -0.37
     DCS
    -0.36
    low
    -0.35
    mbi
    -0.35
    xl
    -0.35
    pa
    -0.35
    POSITIVE LOGITS
     antal
    0.66
     jumlah
    0.60
     Anzahl
    0.59
    исленность
    0.59
     number
    0.59
    AddTagHelper
    0.59
    oubliez
    0.58
     aantal
    0.56
    number
    0.55
     liczba
    0.54
    Act Density 0.075%

    No Known Activations