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

    Neuronpedia

    INDEX
    Explanations

    liver

    np_max-act · gemini-2.0-flash

    The neuron is primarily activated by mentions of “liver” (and closely related terms like “hepatic”) in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    endcode
    -0.07
     الشي
    -0.07
    clas
    -0.07
    ţi
    -0.07
     xấu
    -0.07
    iễ
    -0.07
     melody
    -0.06
     भग
    -0.06
    Done
    -0.06
    Thus
    -0.06
    POSITIVE LOGITS
     liver
    0.13
     Liver
    0.12
    Liver
    0.09
    -INF
    0.07
     рес
    0.07
    Liverpool
    0.07
     logger
    0.07
     Living
    0.07
    刘
    0.07
     Liverpool
    0.07
    Act Density 0.010%

    No Known Activations