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

    Neuronpedia

    INDEX
    Explanations

    list data structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    一是
    0.50
    OH
    0.48
    m
    0.45
    ALS
    0.44
    Ss
    0.44
    EC
    0.44
     repos
    0.43
    C
    0.43
    AC
    0.43
     pek
    0.42
    POSITIVE LOGITS
    housing
    0.47
     немає
    0.46
     இல்லை
    0.45
     ≠
    0.45
     बढ़ाता
    0.44
    ʹ
    0.44
    棲
    0.42
    楽し
    0.41
    ありません
    0.41
    卦
    0.41
    Act Density 0.002%

    No Known Activations