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

    Neuronpedia

    INDEX
    Explanations

    Losing

    np_max-act · gemini-2.0-flash

    The neuron primarily responds to words expressing loss or departure (e.g. “leave,” “lost,” “moving,” “split off”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     зобов
    -0.07
     DependencyProperty
    -0.07
     motto
    -0.07
     faç
    -0.07
     нового
    -0.06
     пан
    -0.06
     Zukunft
    -0.06
     tela
    -0.06
     ак
    -0.06
    	or
    -0.06
    POSITIVE LOGITS
     treat
    0.07
    Scale
    0.07
    np
    0.07
     συνέ
    0.07
     slightly
    0.07
    isspace
    0.06
     Hollow
    0.06
    thern
    0.06
    overs
    0.06
    rey
    0.06
    Act Density 0.040%

    No Known Activations