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

    Neuronpedia

    INDEX
    Explanations

    fitting items together

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    t
    1.23
    ä
    1.04
    s
    1.01
    )=>
    0.98
    ς
    0.89
    ሳሪያ
    0.86
     europé
    0.85
    m
    0.85
    Y
    0.84
    фия
    0.84
    POSITIVE LOGITS
    و
    1.45
    다
    1.41
    uits
    1.14
    ka
    1.11
    ying
    1.09
    iset
    1.07
    ل
    1.02
    ι
    1.01
    ↵↵
    0.99
     Για
    0.94
    Act Density 0.013%

    No Known Activations