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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions and equations related to stochastic processes and modeling

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

    Variables named "x" with a subscript

    np_acts-logits-general · gemini-2.0-flash

    mathematical variables x, y, Phi

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    utkan
    -0.56
    iello
    -0.53
     Rules
    -0.53
     specified
    -0.52
    SPECIFICATIONS
    -0.52
     open
    -0.51
    ír
    -0.51
     Rule
    -0.51
     Dead
    -0.51
     skai
    -0.50
    POSITIVE LOGITS
    ViewFeatures
    0.83
     חיצוניים
    0.74
    parsedMessage
    0.71
     referenties
    0.69
     Wicidata
    0.68
    BeginContext
    0.68
    abestanden
    0.67
    KommentareTeilen
    0.66
    Geplaatst
    0.66
    MemoryWarning
    0.65
    Act Density 1.442%

    No Known Activations