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

    Neuronpedia

    INDEX
    Explanations

    expressing feeling

    np_max-act · gemini-2.0-flash

    The neuron fires on first-person self-references (e.g., “I,” “I’m,” “we’re”), marking sentences where the speaker refers to themselves.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    "http
    -0.07
    Με
    -0.07
    _TWO
    -0.07
    707
    -0.07
    -employed
    -0.06
     Nar
    -0.06
    cw
    -0.06
    jekt
    -0.06
    ств
    -0.06
    comm
    -0.06
    POSITIVE LOGITS
     gratuit
    0.06
     Runtime
    0.06
    ]',↵
    0.06
     représent
    0.06
     사업
    0.06
     groupId
    0.06
    _trade
    0.06
     hesab
    0.06
     Representation
    0.06
     достиг
    0.06
    Act Density 0.055%

    No Known Activations