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

    Neuronpedia

    INDEX
    Explanations

    blood

    np_max-act · gemini-2.0-flash

    The neuron activates on graphic references to blood or bleeding (e.g. “blood,” “drip,” “pool”) indicating it’s detecting vivid descriptions of gore.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ubar
    -0.07
    Nr
    -0.06
     tunnels
    -0.06
     questionnaire
    -0.06
    xDE
    -0.06
     raid
    -0.06
    uxtap
    -0.06
     arbit
    -0.06
     rab
    -0.06
     kad
    -0.06
    POSITIVE LOGITS
     підстав
    0.07
    ��
    0.07
     />
    0.07
     swing
    0.06
    اول
    0.06
     besonders
    0.06
     bilim
    0.06
    ]));
    0.06
    .Utc
    0.06
     defending
    0.06
    Act Density 0.003%

    No Known Activations