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

    Neuronpedia

    INDEX
    Explanations

    mathematical or scientific terms and concepts that involve calculations or measurements

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

    Mathematical or programmatic notation

    np_acts-logits-general · gemini-2.0-flash

    multiple testing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    bootstrapcdn
    -0.44
    SerializedName
    -0.41
     élite
    -0.40
    styleType
    -0.39
    Cryptography
    -0.39
    ﴾
    -0.39
     Audiodateien
    -0.38
     bille
    -0.38
     HasFactory
    -0.38
     catal
    -0.38
    POSITIVE LOGITS
     mijne
    0.47
    IsMutable
    0.45
     yyq
    0.44
     mengal
    0.44
     الرياضيه
    0.43
     paisagem
    0.42
     dotyczy
    0.42
    adaptiveStyles
    0.42
    PYX
    0.41
    msgTypes
    0.41
    Act Density 1.175%

    No Known Activations