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

    Neuronpedia

    INDEX
    Explanations

    information and explanation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ,
    0.50
     A
    0.45
     So
    0.44
     but
    0.44
     and
    0.44
     so
    0.39
     But
    0.39
    ،
    0.39
    …
    0.39
     Now
    0.39
    POSITIVE LOGITS
     previewBuilder
    0.47
     DISPLAYSURF
    0.43
     reactants
    0.42
     photons
    0.41
     autoWatch
    0.41
     thisTrial
    0.41
    ၻ
    0.40
     presenceData
    0.40
     elapse
    0.39
     customPlot
    0.39
    Act Density 0.000%

    No Known Activations