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

    Neuronpedia

    INDEX
    Explanations

    online forum comments

    np_max-act · gemini-2.0-flash

    The neuron fires on evaluative or opinion-bearing words (i.e. adjectives and adverbs expressing judgments or stances).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    念
    -0.07
    _mount
    -0.06
    今
    -0.06
     Elem
    -0.06
    294
    -0.06
    Baseline
    -0.06
    模
    -0.06
     Dreams
    -0.06
     Gate
    -0.06
    .now
    -0.06
    POSITIVE LOGITS
    棋牌
    0.07
     Ник
    0.07
     Chúa
    0.07
     crafting
    0.07
     veter
    0.06
     murky
    0.06
     payday
    0.06
     Regardless
    0.06
     Cassandra
    0.06
     případě
    0.06
    Act Density 0.072%

    No Known Activations