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

    Neuronpedia

    INDEX
    Explanations

    high-frequency occurrences of the word "the."

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

    the [entity name]

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ungsver
    -0.35
     means
    -0.32
    Etimología
    -0.31
    addMessage
    -0.31
     BOW
    -0.30
     needs
    -0.30
    LTR
    -0.29
    -0.29
    UnusedPrivate
    -0.29
    ensuremath
    -0.29
    POSITIVE LOGITS
     وتسجيلات
    0.59
     فريبيس
    0.59
    AndEndTag
    0.58
     Monfieur
    0.57
    ✨:
    0.57
    ⓘ
    0.57
    endpush
    0.55
    IntoConstraints
    0.55
     surla
    0.53
    SharedCtor
    0.52
    Act Density 0.045%

    No Known Activations