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

    Neuronpedia

    INDEX
    Explanations

    stop words

    np_max-act · gemini-2.0-flash

    The neuron activates on phrasing that describes someone being out or limited “because of a … injury,” i.e. mentions of injuries and their causes.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ....
    -0.07
    若
    -0.06
    	random
    -0.06
    今
    -0.06
    竟
    -0.06
    -total
    -0.06
     Liberals
    -0.06
     lá
    -0.06
    esh
    -0.06
     abundance
    -0.06
    POSITIVE LOGITS
     useSelector
    0.07
     風
    0.07
     OnPropertyChanged
    0.06
    іти
    0.06
    (nameof
    0.06
    getName
    0.06
    _REALTYPE
    0.06
     headphone
    0.06
     Matching
    0.06
    zman
    0.06
    Act Density 0.011%

    No Known Activations