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

    Neuronpedia

    INDEX
    Explanations

    Negation

    np_max-act · gemini-2.0-flash

    This neuron detects the presence of the negation “not,” as used in phrasing questions asking “which is not…”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    дивиду
    -0.08
    ють
    -0.07
     Kr
    -0.07
     gearbox
    -0.06
     daher
    -0.06
     bytearray
    -0.06
    _SCR
    -0.06
     повин
    -0.06
    不同
    -0.06
    เกม
    -0.06
    POSITIVE LOGITS
     rentals
    0.07
     диагности
    0.06
    PY
    0.06
     Steam
    0.06
     örnek
    0.06
    attendance
    0.06
    フェ
    0.06
    oller
    0.06
    bic
    0.06
    owo
    0.06
    Act Density 0.007%

    No Known Activations