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

    Neuronpedia

    INDEX
    Explanations

    symbols and notation typically used in mathematical or programming contexts

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

    latex command \smash

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     famí
    -0.40
     oui
    -0.38
    坊
    -0.37
    Kaynakça
    -0.36
    OCO
    -0.36
    amilya
    -0.36
    antası
    -0.35
    Cartney
    -0.35
    DSS
    -0.35
    dx
    -0.34
    POSITIVE LOGITS
    \{\\
    1.27
     <<<<<<<<<<<<<<
    0.79
    uxxxx
    0.67
     للمعارف
    0.61
     שוליים
    0.60
     AssemblyTitle
    0.57
    EndInit
    0.57
    writeHead
    0.57
     CreateTagHelper
    0.56
     AssemblyProduct
    0.54
    Act Density 0.010%

    No Known Activations