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

    Neuronpedia

    INDEX
    Explanations

    Value

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Six
    -0.07
     عص
    -0.07
    試
    -0.06
    かない
    -0.06
    評
    -0.06
    歷
    -0.06
    ửa
    -0.06
     꼭
    -0.06
     Mansion
    -0.06
    rav
    -0.06
    POSITIVE LOGITS
    	pthread
    0.07
    NECTION
    0.07
     SVG
    0.07
     disadvantaged
    0.07
    webkit
    0.07
    archs
    0.07
     Souls
    0.06
     سبک
    0.06
    [".
    0.06
     pants
    0.06
    Act Density 0.000%

    No Known Activations