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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash

    This neuron consistently activates on mentions of someone’s death or murder.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    .textBox
    -0.07
    通知
    -0.07
     Jeho
    -0.06
    	print
    -0.06
     calloc
    -0.06
    orch
    -0.06
     змож
    -0.06
     söz
    -0.06
    xlim
    -0.06
    宣
    -0.06
    POSITIVE LOGITS
    ับต
    0.07
    ynchron
    0.06
     ‎#
    0.06
    tensor
    0.06
    ､↵
    0.06
    uper
    0.06
     AMD
    0.06
    Mix
    0.06
    forum
    0.06
    (with
    0.06
    Act Density 0.036%

    No Known Activations