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

    Neuronpedia

    INDEX
    Explanations

    pytorch.org/get-started/locally

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Vs
    0.39
     हौ
    0.38
     expressed
    0.36
     positiva
    0.35
     gifts
    0.35
     fier
    0.34
    unti
    0.34
     thoughtful
    0.34
     insists
    0.34
    exa
    0.34
    POSITIVE LOGITS
    었는데
    0.45
    法轮
    0.42
    HelloWorld
    0.40
    重新
    0.39
    તર
    0.39
    일까지
    0.39
     redirection
    0.39
     ओळख
    0.38
    আমরা
    0.38
     fade
    0.38
    Act Density 0.000%

    No Known Activations