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

    Neuronpedia

    INDEX
    Explanations

    ss

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	m
    -0.06
     Sin
    -0.06
     trying
    -0.06
     ON
    -0.06
     After
    -0.06
    	b
    -0.06
     gebruik
    -0.06
    晴
    -0.06
    !***
    -0.06
     Patient
    -0.06
    POSITIVE LOGITS
    fifo
    0.07
    .Redis
    0.06
     해외
    0.06
     sigmoid
    0.06
    _Metadata
    0.06
     NAND
    0.06
     sleeves
    0.06
     receptive
    0.06
    ([^
    0.06
    śli
    0.06
    Act Density 0.003%

    No Known Activations