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

    Neuronpedia

    INDEX
    Explanations

    chess moves

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    wei
    0.38
    0
    0.37
    :</
    0.37
    ukk
    0.36
     I
    0.36
     convierte
    0.36
    :",
    0.35
    atori
    0.34
    lire
    0.34
     &
    0.33
    POSITIVE LOGITS
    다
    0.55
    ள்ப
    0.43
    に
    0.43
    on
    0.42
    یع
    0.41
    ی
    0.39
    ле
    0.38
    ილი
    0.38
    رځ
    0.38
    یب
    0.38
    Act Density 0.001%

    No Known Activations