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

    Neuronpedia

    INDEX
    Explanations

    device

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .alignment
    -0.07
     Agility
    -0.06
    retched
    -0.06
    .Im
    -0.06
    .LOGIN
    -0.06
     ATA
    -0.06
     Bor
    -0.06
    配
    -0.06
     bre
    -0.06
     workforce
    -0.06
    POSITIVE LOGITS
     percept
    0.08
     oggi
    0.07
    Orden
    0.07
     sigu
    0.06
     waving
    0.06
    /package
    0.06
     จาก
    0.06
    тр
    0.06
    διο
    0.06
     ocur
    0.06
    Act Density 0.008%

    No Known Activations