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

    Neuronpedia

    INDEX
    Explanations

    Internet conversations

    np_max-act · gemini-2.0-flash

    This neuron detects occurrences of first-person self-references, especially the pronoun “I.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    escription
    -0.07
    رده
    -0.07
    -log
    -0.06
    -valid
    -0.06
    printw
    -0.06
     เจ
    -0.06
     Carrie
    -0.06
     Dell
    -0.06
     pudding
    -0.06
    uds
    -0.06
    POSITIVE LOGITS
     directs
    0.06
     eternity
    0.06
     инт
    0.06
    ()-
    0.06
    oop
    0.06
    refund
    0.06
    トリ
    0.06
    .onNext
    0.06
     Rid
    0.06
    kees
    0.06
    Act Density 0.036%

    No Known Activations