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

    Neuronpedia

    INDEX
    Explanations

    quiet operation or safely drive

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ।
    1.20
     porches
    0.89
     canoes
    0.88
     fusible
    0.86
     drewn
    0.85
    。
    0.83
    ד
    0.82
     ফেল
    0.81
     tuck
    0.80
     ferr
    0.80
    POSITIVE LOGITS
    म
    1.05
    ت
    1.02
    션
    0.91
    ת
    0.90
     其实
    0.90
    هو
    0.89
    你不
    0.87
    नन
    0.86
    نڈ
    0.86
    énergie
    0.86
    Act Density 0.000%

    No Known Activations