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

    Neuronpedia

    INDEX
    Explanations

    approximations and pi

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    linearity
    0.46
     получают
    0.39
    ônia
    0.37
    +(
    0.37
    鬣
    0.37
    ヰ
    0.36
     بنائیں
    0.36
     કરવાનો
    0.36
     cynicism
    0.36
    𝐷
    0.36
    POSITIVE LOGITS
    approx
    0.62
    Approx
    0.53
     approximated
    0.49
     aproximativ
    0.49
     approximate
    0.49
     aprox
    0.48
     approx
    0.48
     ≈
    0.48
     ongeveer
    0.48
     approximates
    0.46
    Act Density 0.000%

    No Known Activations