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

    Neuronpedia

    INDEX
    Explanations

    found

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    transparent
    -0.07
    same
    -0.07
     ổn
    -0.07
    託
    -0.07
    ossa
    -0.07
     camino
    -0.06
     таким
    -0.06
    林
    -0.06
     tablename
    -0.06
    paramref
    -0.06
    POSITIVE LOGITS
    יצו
    0.07
    dıklar
    0.07
    岁时
    0.07
    Psy
    0.06
     bąd
    0.06
    грани
    0.06
    InstantiationException
    0.06
    ABCDEFGHI
    0.06
     hentai
    0.06
    dating
    0.06
    Act Density 0.016%

    No Known Activations