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

    Neuronpedia

    INDEX
    Explanations

    code entity constructors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    rys
    0.46
    ylob
    0.41
    OT
    0.40
    ouver
    0.39
    uco
    0.38
     kolo
    0.38
    oser
    0.38
    OR
    0.38
    ladesh
    0.38
    yl
    0.37
    POSITIVE LOGITS
    ()
    0.64
    (){}
    0.57
    (){
    0.54
     initWith
    0.54
    ())
    0.48
     initWithFrame
    0.47
     ()
    0.46
    ()")
    0.44
     initialise
    0.44
     (){
    0.44
    Act Density 0.006%

    No Known Activations