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

    Neuronpedia

    INDEX
    Explanations

    mathematical equations involving variables and operations.

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

    equations using then

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    كمة
    0.48
    墘
    0.47
    💸
    0.46
    𐰚
    0.45
    💴
    0.45
    硙
    0.45
     생각을
    0.44
    举办
    0.43
     preços
    0.43
     względu
    0.43
    POSITIVE LOGITS
     $\
    0.67
    f
    0.67
    if
    0.65
    q
    0.64
    k
    0.62
    P
    0.61
    D
    0.60
    G
    0.60
     d
    0.59
     M
    0.59
    Act Density 0.164%

    No Known Activations