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

    Neuronpedia

    INDEX
    Explanations

    non-english words and code tokens

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    CLOCK
    0.37
    HAEL
    0.36
    FERENCE
    0.35
    ମ୍
    0.35
    痞
    0.34
    HER
    0.34
    SLOW
    0.34
     каждому
    0.33
    軽量
    0.33
    槌
    0.33
    POSITIVE LOGITS
    ándolo
    0.40
    Toolbar
    0.39
    andolo
    0.37
     चा
    0.34
     দিল্ল
    0.33
     පේශ
    0.33
    ándola
    0.33
    ILayout
    0.33
     दुआ
    0.33
    शोध
    0.32
    Act Density 0.003%

    No Known Activations