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

    Neuronpedia

    INDEX
    Explanations

    terms related to statistical or mathematical functions and their properties

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

    Mathematical or scientific notation

    np_acts-logits-general · gemini-2.0-flash

    mathematical and logical operators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     itſelf
    -0.85
     fubject
    -0.82
     Chriftian
    -0.80
    |}{$
    -0.77
     chofe
    -0.76
     Majefty
    -0.75
     himſelf
    -0.73
     fince
    -0.72
     themſelves
    -0.72
     myſelf
    -0.71
    POSITIVE LOGITS
    mergeFrom
    0.50
    ErrUnexpectedEOF
    0.45
    parseFrom
    0.43
    tonode
    0.40
    typeorm
    0.39
    ати
    0.38
     te
    0.38
    ponses
    0.38
    posedge
    0.38
    numerusform
    0.37
    Act Density 0.459%

    No Known Activations