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

    Neuronpedia

    INDEX
    Explanations

    mathematical calculations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     நடத்த
    0.39
    功夫
    0.37
    conduct
    0.37
     conducta
    0.36
     foram
    0.35
    了他
    0.34
     شدہ
    0.34
    㡀
    0.34
    divers
    0.34
    Divers
    0.34
    POSITIVE LOGITS
     deem
    0.39
     tanh
    0.39
     deel
    0.39
     hesitate
    0.38
     rang
    0.38
    DESIGN
    0.37
     design
    0.37
     naan
    0.37
    esus
    0.37
     نواز
    0.37
    Act Density 0.017%

    No Known Activations