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

    Neuronpedia

    INDEX
    Explanations

    study data

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     zou
    -0.07
     Goals
    -0.07
     emple
    -0.07
     dikke
    -0.06
     rugged
    -0.06
     wrink
    -0.06
     ELECT
    -0.06
     说
    -0.06
    roduction
    -0.06
    енню
    -0.06
    POSITIVE LOGITS
    ματος
    0.06
    _SC
    0.06
    кадем
    0.06
    σεων
    0.06
    .tagName
    0.06
    THIS
    0.06
    .Resize
    0.06
    .shop
    0.06
    ysl
    0.06
    _TRNS
    0.06
    Act Density 0.024%

    No Known Activations