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

    Neuronpedia

    INDEX
    Explanations

    lo-fi, lora, looter

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ليه
    0.43
    वाया
    0.42
    Semif
    0.40
    问题
    0.40
    ূলক
    0.38
    ارق
    0.38
    連続
    0.38
     Telf
    0.38
     SAS
    0.37
     Pirelli
    0.37
    POSITIVE LOGITS
     LO
    0.68
     Lo
    0.66
     lo
    0.65
     ло
    0.65
    Lo
    0.62
     ló
    0.55
     لو
    0.54
    LO
    0.53
     lắng
    0.53
     लो
    0.51
    Act Density 0.017%

    No Known Activations