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

    Neuronpedia

    INDEX
    Explanations

    HTTP methods, roles, categories, units

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    lüğ
    0.29
     حتی
    0.29
    .•
    0.29
     ancak
    0.28
    ât
    0.26
     лично
    0.26
    借助
    0.26
     इसलिए
    0.26
     però
    0.26
    .**
    0.26
    POSITIVE LOGITS
    را
    0.33
    ad
    0.31
    il
    0.29
    으로
    0.28
    クトル
    0.28
    LLS
    0.27
    Forgery
    0.27
    XVI
    0.27
    all
    0.27
    രീ
    0.26
    Act Density 0.801%

    No Known Activations