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

    Neuronpedia

    INDEX
    Explanations

    division of labor

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Computed
    0.45
    ட்டுகள்
    0.43
     conforto
    0.43
    Callable
    0.42
    Italie
    0.39
     nowrap
    0.39
    ото
    0.39
     GLFW
    0.39
    Accuracy
    0.38
     комфор
    0.38
    POSITIVE LOGITS
    cant
    0.41
     next
    0.38
    賃
    0.37
     नस
    0.36
     cant
    0.36
     enabled
    0.36
     having
    0.36
     extensively
    0.36
     못
    0.36
    ocke
    0.36
    Act Density 0.000%

    No Known Activations