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

    Neuronpedia

    INDEX
    Explanations

    uppercase and lowercase letters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    卸
    0.44
    taus
    0.41
     лікар
    0.41
    δί
    0.40
    COMP
    0.40
    ીર
    0.40
     phénomènes
    0.39
    stethoscope
    0.39
    臨床
    0.38
    TUN
    0.38
    POSITIVE LOGITS
     capitalized
    0.97
     capitalization
    0.91
     capitals
    0.91
     Capitals
    0.80
     uppercase
    0.78
     capital
    0.77
     capitalize
    0.77
     Capital
    0.73
     lowercase
    0.73
     kapital
    0.71
    Act Density 0.083%

    No Known Activations