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

    Neuronpedia

    INDEX
    Explanations

    slide

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     CGPoint
    -0.44
    keycode
    -0.43
     plata
    -0.43
     Signalez
    -0.40
    ivis
    -0.40
     sliding
    -0.40
    nelle
    -0.39
    addPreferredGap
    -0.39
     Windows
    -0.38
     slide
    -0.38
    POSITIVE LOGITS
     المعيارى
    0.77
    :✨
    0.76
    storm
    0.59
    breeze
    0.59
    numerusform
    0.57
     Waray
    0.56
    IInterface
    0.56
    RepeatedField
    0.55
    ecap
    0.54
     كومونز
    0.54
    Act Density 0.001%

    No Known Activations