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

    Neuronpedia

    INDEX
    Explanations

    numbers with commas

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     الأحمر
    0.44
     hegemony
    0.43
     Buck
    0.41
     Inspe
    0.40
     Liberal
    0.40
    रा
    0.39
    ನೀ
    0.39
    鹕
    0.39
    ২৮
    0.39
     Yours
    0.38
    POSITIVE LOGITS
     loin
    0.38
     flavonoid
    0.38
     probleml
    0.37
    ገር
    0.37
     پیشہ
    0.36
     unpaired
    0.36
     duquel
    0.36
    atenin
    0.35
     anticoagulant
    0.34
    ować
    0.34
    Act Density 0.002%

    No Known Activations