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

    Neuronpedia

    INDEX
    Explanations

    references to statistical concepts and methods in causal inference

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

    Text inside parentheses, especially citations

    np_acts-logits-general · gemini-2.0-flash

    statistical and probabilistic terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     OMITBAD
    -0.58
     intptr
    -0.58
    httphttps
    -0.54
    хьтан
    -0.53
    Diweddarwch
    -0.52
    GraphicsUnit
    -0.51
     Pakai
    -0.49
    WebElementEntity
    -0.49
     Pardavimas
    -0.48
     desmotivaciones
    -0.47
    POSITIVE LOGITS
     "
    0.42
     "@/
    0.40
    CrossRef
    0.40
    optString
    0.39
     Anfitrión
    0.37
    meta
    0.36
    viewDid
    0.35
    borderSide
    0.35
     total
    0.35
     hen
    0.35
    Act Density 0.774%

    No Known Activations