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

    Neuronpedia

    INDEX
    Explanations

    reporting issues

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     animation
    0.46
     रेड
    0.43
     mashed
    0.42
     styling
    0.42
    -
    0.42
     sewer
    0.41
     entrees
    0.41
     are
    0.41
     ac
    0.41
     sushi
    0.41
    POSITIVE LOGITS
     조건
    0.44
    㕕
    0.42
     Faculty
    0.40
    嫘
    0.40
    ﮟ
    0.39
    തിൽ
    0.39
     مجھے
    0.38
     ব্যর্থ
    0.38
    ErrorInfo
    0.38
    édon
    0.38
    Act Density 0.004%

    No Known Activations