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

    Neuronpedia

    INDEX
    Explanations

    submission

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Mayor
    -0.07
    acio
    -0.07
    	actor
    -0.07
     native
    -0.06
    otor
    -0.06
    .Engine
    -0.06
    傲
    -0.06
     pastor
    -0.06
    母亲
    -0.06
    搖
    -0.06
    POSITIVE LOGITS
    それぞれ
    0.08
    ᠲ
    0.07
     Giriş
    0.07
     ślub
    0.07
    ))[
    0.07
    ))),↵
    0.07
     responses
    0.07
    这些人
    0.07
    .comm
    0.06
     plush
    0.06
    Act Density 0.009%

    No Known Activations