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

    Neuronpedia

    INDEX
    Explanations

    my best

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    íte
    0.49
     unthinkable
    0.42
    まさに
    0.41
    slightly
    0.41
     vár
    0.40
    ior
    0.40
     coisas
    0.39
    वर्ग
    0.39
    Perhaps
    0.39
     inconceivable
    0.39
    POSITIVE LOGITS
     best
    1.34
    best
    1.15
     최대한
    1.01
     Best
    0.88
    ベスト
    0.86
    尽量
    0.86
    尽可能
    0.86
    最佳
    0.85
     بهترین
    0.85
     BEST
    0.84
    Act Density 0.008%

    No Known Activations