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

    Neuronpedia

    INDEX
    Explanations

    mathematical notation and symbols related to statistics and probability

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

    mathematical symbols and variables

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ConstraintMaker
    -0.58
    MessageTagHelper
    -0.54
     surla
    -0.54
    EndInit
    -0.53
     ddelweddau
    -0.53
    enderror
    -0.51
    keyColumn
    -0.50
    principalColumn
    -0.49
    invokeLater
    -0.49
    IContainer
    -0.48
    POSITIVE LOGITS
     bless
    0.43
    enumi
    0.36
     ErrIntOverflow
    0.35
     Bless
    0.34
     temp
    0.34
     Limestone
    0.33
     meri
    0.33
    心
    0.32
    úmer
    0.32
    yych
    0.32
    Act Density 0.753%

    No Known Activations