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

    Neuronpedia

    INDEX
    Explanations

    biographical/narrative texts

    np_max-act · gemini-2.0-flash

    The neuron fires on narrative character references—i.e. mentions of characters (names or pronouns) together with their actions or emotions.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     post
    -0.07
    ुत
    -0.07
     read
    -0.07
     v
    -0.07
    'aut
    -0.07
     lyrics
    -0.06
     literary
    -0.06
    _qu
    -0.06
     enjoyed
    -0.06
    .mybatisplus
    -0.06
    POSITIVE LOGITS
    █
    0.07
     Problem
    0.07
    .completed
    0.06
     concerted
    0.06
    63
    0.06
    ordion
    0.06
    หา
    0.06
     shredd
    0.06
    -mobile
    0.06
    /helper
    0.06
    Act Density 0.170%

    No Known Activations