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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash

    The neuron primarily fires on the first‐person pronoun “I,” marking sentences where the speaker refers to themselves.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     residency
    -0.06
     cấu
    -0.06
     달
    -0.06
    ermann
    -0.06
    <Contact
    -0.06
    Merchant
    -0.06
     フ
    -0.06
    略
    -0.06
    (history
    -0.06
    alpha
    -0.06
    POSITIVE LOGITS
    \core
    0.07
    _ic
    0.07
    .Material
    0.06
    nda
    0.06
    zure
    0.06
     pe
    0.06
    OSH
    0.06
    rib
    0.06
     ime
    0.06
    _APP
    0.06
    Act Density 0.134%

    No Known Activations