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

    Neuronpedia

    INDEX
    Explanations

    file paths and identifiers in code or configuration settings

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

    file paths and urls

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     signed
    -0.47
     ilmo
    -0.38
    bebasan
    -0.37
    bcryptjs
    -0.37
    pruch
    -0.37
     Erişim
    -0.34
    psum
    -0.34
    soka
    -0.34
    ite
    -0.34
     degree
    -0.34
    POSITIVE LOGITS
    hyrchwyd
    0.71
    بوابة
    0.67
     informée
    0.64
    styleable
    0.63
    AddTagHelper
    0.63
    TagNumber
    0.63
    OGND
    0.59
    Bakgrunnsstoff
    0.58
     imageNamed
    0.58
    KommentareTeilen
    0.57
    Act Density 0.014%

    No Known Activations