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

    Neuronpedia

    INDEX
    Explanations

    should be

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     sheer
    0.48
    ت
    0.42
    ein
    0.41
     كذلك
    0.41
     kohta
    0.40
    Certainly
    0.39
    ele
    0.39
    Basically
    0.39
    inig
    0.39
     forth
    0.38
    POSITIVE LOGITS
    ف
    0.51
    pageX
    0.45
     Percent
    0.44
     mutate
    0.44
    uglify
    0.43
     TestBed
    0.42
     mathbf
    0.41
     aspectRatio
    0.41
     phối
    0.41
    ombie
    0.40
    Act Density 0.441%

    No Known Activations