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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions and equations involving functions and variables

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

    f(x) equations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Roskov
    -0.63
     gyhoeddwyd
    -0.58
     ब्रेकडाउन
    -0.53
     Италијани
    -0.52
    GEBURTSDATUM
    -0.51
    IsMutable
    -0.51
     ویکی‌پدی
    -0.48
     '\\;'
    -0.48
     cherchés
    -0.47
     ویکی‌پدیای
    -0.47
    POSITIVE LOGITS
     femininos
    0.48
     Geiſt
    0.48
     unsuccessful
    0.47
     excited
    0.45
     Geſch
    0.45
    ulls
    0.44
    GetEnumerator
    0.43
    bete
    0.43
     Waſſer
    0.43
     convoluted
    0.43
    Act Density 0.743%

    No Known Activations