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

    Neuronpedia

    INDEX
    Explanations

    аж

    np_max-act · gemini-2.0-flash

    this neuron activates on Portuguese verbs describing the action of pressing or clicking (e.g. “apertando,” “pressiona”)

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    //---------------------------------------------------------------------------↵
    -0.07
     پژوهش
    -0.07
     женщина
    -0.07
    есть
    -0.06
    окс
    -0.06
    ือด
    -0.06
    argon
    -0.06
     kỷ
    -0.06
     veřej
    -0.06
     Cox
    -0.06
    POSITIVE LOGITS
     pressed
    0.09
     stuffed
    0.07
     presses
    0.07
    Pressure
    0.07
     Spr
    0.06
    /Dk
    0.06
    0.06
     FloatingActionButton
    0.06
     utter
    0.06
    him
    0.06
    Act Density 0.017%

    No Known Activations