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

    Neuronpedia

    INDEX
    Explanations

    website, USA, called, Click

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    erné
    0.40
     России
    0.38
    tral
    0.36
    дру
    0.35
    ová
    0.34
     Ezra
    0.34
     வலு
    0.34
     Ai
    0.33
    рея
    0.33
    ore
    0.33
    POSITIVE LOGITS
    ():
    0.50
    没有什么
    0.48
    ไม่มี
    0.47
     ():
    0.45
     🙂
    0.45
    無需
    0.44
    无需
    0.43
    ();
    0.42
    ":"","
    0.42
     그대로
    0.42
    Act Density 0.056%

    No Known Activations