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

    Neuronpedia

    INDEX
    Explanations

    personal reflections

    np_max-act · gemini-2.0-flash

    This neuron detects the presence of first-person references—especially the pronoun “I.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    .SetFloat
    -0.07
     Wayne
    -0.06
    "]);↵
    -0.06
    Used
    -0.06
     �
    -0.06
    盒
    -0.06
    oston
    -0.06
     ethic
    -0.06
    _encode
    -0.06
     Far
    -0.06
    POSITIVE LOGITS
    ραση
    0.07
    _ATTACHMENT
    0.06
     виход
    0.06
     Configure
    0.06
    одейств
    0.06
    مز
    0.06
    zend
    0.06
     جلس
    0.06
    IGHL
    0.06
     муж
    0.06
    Act Density 0.060%

    No Known Activations