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

    Neuronpedia

    INDEX
    Explanations

    mathematical symbols and variables in equations and expressions

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

    Greek letters in math notation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     فريبيس
    -0.59
     المعيارى
    -0.57
     Continu
    -0.56
     صوتيه
    -0.56
    Tikang
    -0.55
     Wikimedijinoj
    -0.54
    ...,
    -0.54
    RenderAtEndOf
    -0.54
     ...,
    -0.53
    IntoConstraints
    -0.53
    POSITIVE LOGITS
    œil
    0.55
     desapar
    0.50
    sigma
    0.50
    {§
    0.49
     uVar
    0.45
    NetworkInfo
    0.45
    Omega
    0.42
    ('/');
    0.42
     blik
    0.41
    rho
    0.41
    Act Density 0.521%

    No Known Activations