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

    Neuronpedia

    INDEX
    Explanations

    python except as e

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ኩል
    0.45
    acotta
    0.40
    Tren
    0.40
    studies
    0.40
    Studies
    0.39
    OGND
    0.39
    ابات
    0.36
    स्पिर
    0.36
    EMP
    0.36
     Studies
    0.35
    POSITIVE LOGITS
     e
    1.42
     е
    0.96
    e
    0.82
     E
    0.75
     exp
    0.75
    ｅ
    0.68
     ex
    0.67
     excepc
    0.67
    Exception
    0.67
     expt
    0.65
    Act Density 0.012%

    No Known Activations