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

    Neuronpedia

    INDEX
    Explanations

    conversational interjections

    np_max-act · gemini-2.0-flash

    The neuron responds to first-person subjective/emotional statements (e.g., “I’m jealous,” “I hope,” “thanks,” “feeling”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ilded
    -0.07
    лых
    -0.07
    ¶¶
    -0.06
    енко
    -0.06
    تز
    -0.06
    allon
    -0.06
     Watts
    -0.06
    _node
    -0.06
    ols
    -0.06
    />.
    -0.06
    POSITIVE LOGITS
     √
    0.07
     corporation
    0.07
     上涨
    0.07
    杂
    0.07
     ως
    0.07
    ilog
    0.06
    .fillText
    0.06
    OrUpdate
    0.06
     ای
    0.06
     SHALL
    0.06
    Act Density 0.054%

    No Known Activations