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

    Neuronpedia

    INDEX
    Explanations

    Dec

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	if
    -0.07
    sob
    -0.07
     lập
    -0.07
    Drag
    -0.06
    William
    -0.06
     getType
    -0.06
     incompetence
    -0.06
     biết
    -0.06
     misplaced
    -0.06
    지만
    -0.06
    POSITIVE LOGITS
     decree
    0.08
    Decoder
    0.08
    .Dec
    0.08
    цуз
    0.07
     DEC
    0.07
    daq
    0.07
    Dec
    0.07
     dec
    0.07
    -Dec
    0.07
     Dec
    0.07
    Act Density 0.044%

    No Known Activations