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

    Neuronpedia

    INDEX
    Explanations

    figurative language

    np_max-act · gemini-2.0-flash

    This neuron detects instructions about using “figures of speech.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    紙
    -0.06
     nella
    -0.06
    ッシュ
    -0.06
     annoying
    -0.06
    fon
    -0.06
    tingham
    -0.06
    ประกาศ
    -0.06
    оны
    -0.06
    _MISS
    -0.06
     ganze
    -0.06
    POSITIVE LOGITS
    ΗΡ
    0.07
    getInstance
    0.07
     trí
    0.07
     Вот
    0.07
    popover
    0.06
    odal
    0.06
     Deg
    0.06
     resembled
    0.06
     strategies
    0.06
     홈
    0.06
    Act Density 0.011%

    No Known Activations