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

    Neuronpedia

    INDEX
    Explanations

    let me know

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     plt
    0.35
    0.35
     (
    0.35
     +
    0.35
     +.
    0.33
     ("/
    0.33
     FLAG
    0.33
    ্
    0.32
     ("
    0.32
     যুক্তরাজ
    0.32
    POSITIVE LOGITS
    га
    0.40
     demás
    0.38
    ვის
    0.37
    த்தின்
    0.36
    don
    0.33
    izon
    0.33
    кри
    0.32
    жем
    0.32
     rimane
    0.32
     പിന്നെ
    0.32
    Act Density 0.112%

    No Known Activations