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

    Neuronpedia

    INDEX
    Explanations

    programming keywords (reg, call, sort)

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    🏔
    0.28
    啭
    0.28
     পরিশ
    0.28
     প্রয়োজনে
    0.26
    谛
    0.26
    棂
    0.26
    ajjati
    0.25
     නිෂ්
    0.25
    謾
    0.25
    黢
    0.25
    POSITIVE LOGITS
    8
    0.50
    5
    0.48
    9
    0.46
    4
    0.46
    6
    0.45
    7
    0.44
    3
    0.40
     (
    0.38
    （
    0.34
    -
    0.33
    Act Density 0.553%

    No Known Activations