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

    Neuronpedia

    INDEX
    Explanations

    pro

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Sat
    -0.08
    quip
    -0.07
    ś
    -0.06
    oken
    -0.06
    osaur
    -0.06
    Latitude
    -0.06
     školy
    -0.06
    様
    -0.06
    лиц
    -0.06
     nikdo
    -0.06
    POSITIVE LOGITS
     lim
    0.06
     flyer
    0.06
    .graph
    0.06
    (constants
    0.06
    eson
    0.06
     ((__
    0.06
    	points
    0.06
    _charge
    0.06
     muscles
    0.06
     assembler
    0.06
    Act Density 0.006%

    No Known Activations