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

    Neuronpedia

    INDEX
    Explanations

    body rotation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Reliability
    0.46
    趙
    0.46
     reliability
    0.40
     Rule
    0.39
    नात
    0.38
     turnaround
    0.37
     मुहूर्त
    0.37
     INVEST
    0.36
    ibus
    0.36
     prawo
    0.35
    POSITIVE LOGITS
     شکل
    0.42
    ẖ
    0.41
    rogenic
    0.40
     carbonic
    0.39
     britt
    0.39
    varian
    0.38
    0.38
     cinco
    0.37
     orgánica
    0.37
     ори
    0.36
    Act Density 0.002%

    No Known Activations