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

    Neuronpedia

    INDEX
    Explanations

    code and science

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     enfans
    -0.81
     Grecs
    -0.79
     religieuses
    -0.77
     définiti
    -0.75
     colorés
    -0.75
     avoient
    -0.75
     africains
    -0.74
     prêtres
    -0.74
     sauvages
    -0.73
     quantités
    -0.73
    POSITIVE LOGITS
     about
    0.65
     Audiodateien
    0.60
    #![
    0.60
    تقاوى
    0.55
    bootstrapcdn
    0.52
    Pyx
    0.52
     some
    0.49
    makeConstraints
    0.47
     CURLOPT
    0.45
     sum
    0.44
    Act Density 0.000%

    No Known Activations