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

    Neuronpedia

    INDEX
    Explanations

    list numbers followed by periods

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    等の
    0.45
     எல்லாம்
    0.43
     등의
    0.43
    lerinde
    0.41
    -,
    0.40
    等的
    0.39
    等が
    0.39
     등으로
    0.39
     около
    0.38
    <unused72>
    0.38
    POSITIVE LOGITS
    ៕
    0.37
    Ī
    0.36
    ข้อง
    0.34
    ("'
    0.33
     excerpt
    0.33
     
    0.33
    Papa
    0.33
    Chile
    0.32
    Ottawa
    0.32
     .”
    0.32
    Act Density 0.012%

    No Known Activations