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

    Neuronpedia

    INDEX
    Explanations

    punctuation and formatting elements commonly used in academic citations or references

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

    numbers after colons

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nahilalakip
    -0.69
    UnusedPrivate
    -0.68
     فريبيس
    -0.63
    pantalón
    -0.61
     HasFactory
    -0.61
    BagConstraints
    -0.60
     CommonModule
    -0.60
     resourceCulture
    -0.59
     pinulongan
    -0.58
     }{@
    -0.57
    POSITIVE LOGITS
    RSpec
    0.39
    setVerticalGroup
    0.38
    Abstract
    0.37
    Aholisi
    0.34
    passphrase
    0.31
    2
    0.31
    1
    0.31
    TestBed
    0.31
    6
    0.30
    ParseException
    0.28
    Act Density 0.056%

    No Known Activations