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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash

    This neuron detects first-person perspective content or instructions (mentions of "first person"/POV and occurrences of the pronoun "I").

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Negative Logits
     derived
    -0.07
     correct
    -0.06
     larger
    -0.06
    :no
    -0.06
    _compat
    -0.06
     channels
    -0.06
     hardest
    -0.06
     resistant
    -0.06
    на
    -0.06
     memo
    -0.06
    POSITIVE LOGITS
    /:
    0.07
    categoryId
    0.07
     slog
    0.06
    ΑΠ
    0.06
    PreparedStatement
    0.06
    )size
    0.06
    ‌ب
    0.06
     initWith
    0.06
    )initWith
    0.06
     الش
    0.06
    Act Density 0.089%

    No Known Activations