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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     сім
    -0.06
    �
    -0.06
     bilder
    -0.06
    انس
    -0.06
     mining
    -0.06
     Sadece
    -0.06
     små
    -0.06
     quienes
    -0.06
    ardım
    -0.06
     Gdk
    -0.06
    POSITIVE LOGITS
    (ang
    0.07
     billing
    0.07
    [mid
    0.07
     automatically
    0.06
     enrol
    0.06
    normalized
    0.06
    (routes
    0.06
     Experiment
    0.06
     ballet
    0.06
    uzione
    0.06
    Act Density 0.005%

    No Known Activations