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

    Neuronpedia

    INDEX
    Explanations

    terms related to licensing and distribution in software

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

    redistribute it and/or modify it

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    isalpha
    -0.35
     Arias
    -0.35
    kuat
    -0.35
     foams
    -0.34
     Orgel
    -0.33
     livrer
    -0.33
    搞
    -0.33
    ꇴ
    -0.33
     payé
    -0.33
     jupe
    -0.32
    POSITIVE LOGITS
    ublic
    2.20
    UBLIC
    1.16
    enderror
    1.03
     CreateTagHelper
    0.99
    LookAnd
    0.95
    EDEFAULT
    0.90
    солю
    0.88
     Chwiliwch
    0.85
    rrggbb
    0.85
    SharedCtor
    0.82
    Act Density 0.002%

    No Known Activations