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

    Neuronpedia

    INDEX
    Explanations

    mean age years

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ાં
    -0.88
     so
    -0.84
    acer
    -0.83
    ÜR
    -0.83
    aggi
    -0.82
    次は
    -0.79
     terjangkau
    -0.79
    achuca
    -0.78
    executeUpdate
    -0.78
    ಟ್
    -0.77
    POSITIVE LOGITS
    still
    1.01
    median
    0.94
     still
    0.91
    före
    0.86
    んでしょう
    0.86
     median
    0.85
    riceps
    0.81
     describir
    0.81
    を持っている
    0.80
    categorical
    0.79
    Act Density 0.006%

    No Known Activations