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

    Neuronpedia

    INDEX
    Explanations

    Hello World and code examples

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     portions
    0.39
     cleaved
    0.38
    idxs
    0.36
     plugged
    0.36
    ienna
    0.35
     insinu
    0.35
    दाना
    0.34
     presumed
    0.34
     spod
    0.34
     spared
    0.33
    POSITIVE LOGITS
    HelloWorld
    1.04
    简单的
    0.98
     Hello
    0.96
    Hello
    0.94
     hello
    0.93
    hello
    0.88
    simple
    0.87
     HelloWorld
    0.87
     간단
    0.86
    簡單
    0.85
    Act Density 0.022%

    No Known Activations