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

    Neuronpedia

    INDEX
    Explanations

    lists quantities and states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Daher
    0.43
    渙
    0.42
    nahi
    0.39
    捷
    0.39
    启动
    0.39
    佷
    0.38
     adopting
    0.38
     வலி
    0.38
     Clk
    0.38
     Ее
    0.37
    POSITIVE LOGITS
     échanc
    0.42
     {
    0.37
    äng
    0.36
    {.
    0.36
    (?:
    0.36
    öff
    0.36
     মেয়ে
    0.36
     contextual
    0.35
     शख्स
    0.35
    require
    0.35
    Act Density 0.000%

    No Known Activations