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

    Neuronpedia

    INDEX
    Explanations

    tolerance and diversity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    s
    1.13
    nummer
    1.00
    canceled
    0.93
    n
    0.93
    ان
    0.92
    ים
    0.90
    tor
    0.89
    ties
    0.86
    u
    0.86
    ्स
    0.85
    POSITIVE LOGITS
     tolerance
    1.23
     Tolerance
    1.13
    Tolerance
    1.10
    '
    1.10
     Toler
    1.02
    (
    0.96
     toler
    0.96
     for
    0.91
     tolerancia
    0.84
     tolerant
    0.78
    Act Density 0.006%

    No Known Activations