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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     saldırı
    -0.06
    iterals
    -0.06
    (condition
    -0.06
    =obj
    -0.06
    =["
    -0.06
    (L
    -0.06
     DY
    -0.06
     officials
    -0.06
    나무
    -0.06
     #+#
    -0.06
    POSITIVE LOGITS
    utta
    0.07
    ятие
    0.07
    	UINT
    0.07
     घटन
    0.06
    شار
    0.06
    Assistant
    0.06
     continual
    0.06
     MASTER
    0.06
    DATE
    0.06
     quant
    0.06
    Act Density 0.219%

    No Known Activations