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

    Neuronpedia

    INDEX
    Explanations

    references to documentation and licensing information

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

    code comments and structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AntiForgeryToken
    -0.47
    bootstrapcdn
    -0.46
    kegaard
    -0.45
     Gep
    -0.45
    SqlClient
    -0.44
     للمعارف
    -0.43
    ViewFeatures
    -0.43
    󠁣
    -0.43
    transQ
    -0.43
     Haddad
    -0.42
    POSITIVE LOGITS
    ✨:
    0.60
    Kanpo
    0.44
    CrossRef
    0.44
    Rohy
    0.37
    OGND
    0.36
     päät
    0.36
     intptr
    0.35
     surla
    0.35
     klart
    0.35
    :',
    0.34
    Act Density 0.045%

    No Known Activations