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

    Neuronpedia

    INDEX
    Explanations

    composition

    np_max-act · gemini-2.0-flash

    This neuron detects mentions of “compose”/“composition” (and its morphological variants like “composing”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Beans
    -0.07
     Skype
    -0.06
    _war
    -0.06
     mosquito
    -0.06
    utting
    -0.06
    itation
    -0.06
     석
    -0.06
     leans
    -0.06
     rotating
    -0.06
     anticipation
    -0.06
    POSITIVE LOGITS
     aktuální
    0.07
    (Layout
    0.06
     tegen
    0.06
     JOptionPane
    0.06
    데이트
    0.06
     reviewer
    0.06
    reset
    0.06
     ViewGroup
    0.06
     fotoğraf
    0.06
    Chocolate
    0.06
    Act Density 0.006%

    No Known Activations