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

    Neuronpedia

    INDEX
    Explanations

    code and descriptions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     nam
    -0.07
     Крім
    -0.06
     редак
    -0.06
    .П
    -0.06
     şek
    -0.06
    ندق
    -0.06
     дозвол
    -0.06
    mnop
    -0.06
    shade
    -0.06
     اوت
    -0.06
    POSITIVE LOGITS
    child
    0.07
    edes
    0.07
    cx
    0.07
    AffineTransform
    0.06
    .products
    0.06
    proposal
    0.06
    Value
    0.06
    ud
    0.06
    	ar
    0.06
     bulk
    0.06
    Act Density 0.000%

    No Known Activations