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

    Neuronpedia

    INDEX
    Explanations

    mathematical relationships and proportionality in scientific concepts

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

    Mathematical formulas and expressions

    np_acts-logits-general · gemini-2.0-flash

    inverse, reciprocal, and proportions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     تضيفلها
    -0.57
    BeginContext
    -0.51
    rhein
    -0.48
    wag
    -0.47
     grø
    -0.46
    พล
    -0.45
    teren
    -0.42
    全文
    -0.41
     시
    -0.41
     forma
    -0.41
    POSITIVE LOGITS
     reciprocal
    1.35
     inverse
    1.28
     inversely
    1.09
     Recipro
    1.05
     inversa
    1.04
     Inverse
    1.03
    inverse
    1.00
     reciproc
    0.97
     recipro
    0.93
    Inverse
    0.89
    Act Density 0.733%

    No Known Activations