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

    Neuronpedia

    INDEX
    Explanations

    random .Next()

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    利き
    0.40
     escuch
    0.39
    ี้ยว
    0.38
    输
    0.36
    imshow
    0.36
    听
    0.36
    沉默
    0.36
     услы
    0.35
     رائے
    0.35
     listeners
    0.34
    POSITIVE LOGITS
     Next
    0.45
    Next
    0.44
    tick
    0.44
     Genetics
    0.41
    里克
    0.41
     genetics
    0.40
     beside
    0.40
    nextDouble
    0.40
    ORE
    0.40
    otional
    0.39
    Act Density 0.004%

    No Known Activations