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

    Neuronpedia

    INDEX
    Explanations

    DUNE AI helpful proteins

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     परेश
    0.49
    菽
    0.48
     Guo
    0.44
    ुलर
    0.43
     BSP
    0.42
    قة
    0.42
     Razer
    0.42
     Hold
    0.41
    पिंग
    0.41
    ეთ
    0.41
    POSITIVE LOGITS
     তাদেরকে
    0.40
    គឺ
    0.40
    uits
    0.39
     اجمع
    0.39
    crab
    0.39
     sleeping
    0.38
     thi
    0.38
    mari
    0.38
    oak
    0.38
     oak
    0.37
    Act Density 5.007%

    No Known Activations