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

    Neuronpedia

    INDEX
    Explanations

    this followed by explains/defines

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    يل
    2.04
    क्स्ट
    2.02
    ற்கு
    1.98
    ্যোগ
    1.96
    ن
    1.90
    的环境
    1.88
    elsch
    1.87
    Н
    1.85
    ଠ
    1.85
     munt
    1.84
    POSITIVE LOGITS
    т
    2.52
    sman
    2.44
    s
    2.37
    क
    2.29
    saf
    2.15
    gger
    2.00
    sess
    1.98
    sou
    1.95
    sampled
    1.93
    sid
    1.93
    Act Density 0.610%

    No Known Activations