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

    Neuronpedia

    INDEX
    Explanations

    tertiary education / operator

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ป์
    2.22
    ف
    2.16
     불구하고
    1.91
    am
    1.88
    ان
    1.79
    .
    1.76
    ى
    1.74
    os
    1.73
    ー
    1.73
    m
    1.70
    POSITIVE LOGITS
     grados
    1.95
    கு
    1.91
     complejos
    1.86
    ח
    1.85
    Еще
    1.82
    нку
    1.79
     mismos
    1.74
    IK
    1.73
     coalgebras
    1.73
    퓰
    1.72
    Act Density 0.005%

    No Known Activations