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

    Neuronpedia

    INDEX
    Explanations

    it

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     quasi
    -0.07
    toy
    -0.06
     sabot
    -0.06
     Li
    -0.06
     перший
    -0.06
     дра
    -0.06
    [tmp
    -0.06
    	curl
    -0.06
    Li
    -0.06
    ए
    -0.06
    POSITIVE LOGITS
    enna
    0.06
    ר
    0.06
    索
    0.06
    oolStrip
    0.06
    
    0.06
     işi
    0.06
     kola
    0.06
     Unlock
    0.06
     RAM
    0.06
     measurements
    0.06
    Act Density 0.000%

    No Known Activations