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

    Neuronpedia

    INDEX
    Explanations

    flags and parameters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    九
    0.43
    ９
    0.42
    兩
    0.42
    عمال
    0.41
    ８
    0.41
    รุ่น
    0.40
    八
    0.40
     九
    0.39
    ۴
    0.39
     फोर
    0.39
    POSITIVE LOGITS
    6
    0.40
    ANK
    0.36
    alth
    0.34
    add
    0.34
    Add
    0.33
     casc
    0.33
    情報の
    0.33
    xxxxx
    0.33
    Token
    0.33
    Subscribe
    0.33
    Act Density 0.003%

    No Known Activations