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

    Neuronpedia

    INDEX
    Explanations

    Java code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .examples
    -0.07
    ору
    -0.07
    Pooling
    -0.07
    ey
    -0.07
    lte
    -0.07
    .EOF
    -0.07
     Bulg
    -0.07
    develop
    -0.06
     Laz
    -0.06
     toned
    -0.06
    POSITIVE LOGITS
    胎
    0.06
    	on
    0.06
    ?",↵
    0.06
    	ev
    0.06
    \
    0.06
    .The
    0.06
     comeback
    0.06
    516
    0.06
    .AutoScale
    0.06
     proposition
    0.05
    Act Density 0.034%

    No Known Activations