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

    Neuronpedia

    INDEX
    Explanations

    handc

    np_max-act · gemini-2.0-flash

    The neuron chiefly activates on words describing physical police actions (e.g. patting down, handcuffing, slamming, punching).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     humili
    -0.07
    ocrisy
    -0.07
     土
    -0.06
    eca
    -0.06
    .AttributeSet
    -0.06
     пол
    -0.06
    될
    -0.06
    882
    -0.06
    hetto
    -0.06
     intervene
    -0.06
    POSITIVE LOGITS
     Blast
    0.07
    =list
    0.07
    ']=
    0.07
    creating
    0.07
     снова
    0.06
    -validate
    0.06
    VENTORY
    0.06
    _;
↵
    0.06
     Printing
    0.06
    ेहर
    0.06
    Act Density 0.007%

    No Known Activations