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

    Neuronpedia

    INDEX
    Explanations

    bone fractures

    np_max-act · gemini-2.0-flash

    The neuron detects mentions of physical injuries or bodily harm (e.g., broken bones, ankle injuries, concussions).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    	param
    -0.07
     رضا
    -0.06
    ترین
    -0.06
    络
    -0.06
    (Json
    -0.06
    aise
    -0.06
    -hop
    -0.06
    q
    -0.06
    458
    -0.06
    侍
    -0.05
    POSITIVE LOGITS
     algum
    0.07
    Knowing
    0.07
     cara
    0.07
    �
    0.06
    someone
    0.06
    _cf
    0.06
    ốt
    0.06
     somewhere
    0.06
    ocê
    0.06
    riv
    0.06
    Act Density 0.009%

    No Known Activations