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

    Neuronpedia

    INDEX
    Explanations

    symbols and notations commonly used in mathematical proofs and formulations

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

    Greek letters (gamma, lambda, nu)

    np_acts-logits-general · gemini-2.0-flash

    greek letters followed by punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     cherchés
    -0.69
     ویکی‌پدی
    -0.67
    хьтан
    -0.67
    ImageContext
    -0.61
    DebuggerNonUser
    -0.58
    دانشنامهٔ
    -0.57
     khe
    -0.55
    webElementXpaths
    -0.54
     فريبيس
    -0.54
     للمعارف
    -0.53
    POSITIVE LOGITS
     _{
    0.57
    _{
    0.54
    providedIn
    0.48
    deaux
    0.48
    Nhưng
    0.47
    wirkt
    0.47
    _{\
    0.47
     McKe
    0.46
     _{\
    0.46
     informes
    0.46
    Act Density 1.019%

    No Known Activations