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

    Neuronpedia

    INDEX
    Explanations

    explanation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AK
    1.46
    它
    1.46
    tellers
    1.45
    于是
    1.38
    OUT
    1.22
    atures
    1.21
    sticks
    1.20
    AKT
    1.20
     مطرح
    1.19
    𝐖
    1.19
    POSITIVE LOGITS
    т
    1.48
    क
    1.45
    近い
    1.35
    inė
    1.33
    ية
    1.31
    ir
    1.27
    けた
    1.26
    σό
    1.26
    ल
    1.25
     কিন্ত
    1.24
    Act Density 0.006%

    No Known Activations