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

    Neuronpedia

    INDEX
    Explanations

    commands or functions typically associated with programming or document formatting

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

    legal or political phrasing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ome
    -0.35
     թվական
    -0.35
     mathvariant
    -0.32
    atak
    -0.32
    en
    -0.31
     cuenta
    -0.30
     ana
    -0.30
     mor
    -0.30
     ten
    -0.29
    شون
    -0.29
    POSITIVE LOGITS
    1.45
     HasFactory
    0.64
    KommentareTeilen
    0.64
    EndProject
    0.64
    featureID
    0.64
    -------
    0.63
     ujednoznacz
    0.63
    Хьажоргаш
    0.61
    PreExecute
    0.59
    期刊论文
    0.58
    Act Density 0.006%

    No Known Activations