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

    Neuronpedia

    INDEX
    Explanations

    每

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    plus
    -0.07
     quant
    -0.07
    zipcode
    -0.07
     bes
    -0.07
    -info
    -0.07
     CONS
    -0.07
     subject
    -0.07
    exp
    -0.06
    law
    -0.06
     packageName
    -0.06
    POSITIVE LOGITS
    每
    0.29
     每
    0.24
    ，每
    0.20
    某
    0.14
    毎
    0.11
    哪
    0.10
     매
    0.09
    ，这
    0.09
     这
    0.08
    各
    0.08
    Act Density 0.004%

    No Known Activations