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

    Neuronpedia

    INDEX
    Explanations

    argumentative text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	date
    -0.07
     Graphic
    -0.07
    점
    -0.06
     Format
    -0.06
     있
    -0.06
     Deposit
    -0.06
     Cow
    -0.06
    Potential
    -0.06
     верх
    -0.06
     hình
    -0.06
    POSITIVE LOGITS
     трь
    0.07
    memset
    0.06
     Garmin
    0.06
    abelle
    0.06
    Raster
    0.06
     SharedModule
    0.06
     fallen
    0.06
    protobuf
    0.06
    दर
    0.06
    	EIF
    0.06
    Act Density 0.187%

    No Known Activations