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

    Neuronpedia

    INDEX
    Explanations

    code structure and punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Doppler
    0.38
     Sk
    0.38
    Begriffsklär
    0.38
     Stem
    0.37
     Indian
    0.36
     bebé
    0.35
     F
    0.35
     firme
    0.35
    답니다
    0.34
     Hy
    0.34
    POSITIVE LOGITS
    для
    0.42
    ോഷ
    0.40
     със
    0.40
     Функ
    0.40
    ۾
    0.39
     duż
    0.39
    dengan
    0.39
    类型
    0.38
    теров
    0.38
    णासाठी
    0.38
    Act Density 0.145%

    No Known Activations