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

    Neuronpedia

    INDEX
    Explanations

    programming code/errors

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Pavel
    -0.06
     เขต
    -0.06
     assembler
    -0.06
     tensorflow
    -0.06
    臣
    -0.06
    řejmě
    -0.06
     narcotics
    -0.06
    bundle
    -0.06
    ९
    -0.06
     مدر
    -0.06
    POSITIVE LOGITS
     corrections
    0.06
    ी.
    0.06
     versatility
    0.06
     dumps
    0.06
     ใน
    0.06
    .Brand
    0.06
     diferencia
    0.06
     dental
    0.06
     twee
    0.06
    办法
    0.06
    Act Density 0.563%

    No Known Activations