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

    Neuronpedia

    INDEX
    Explanations

    key employee, premises, contents

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    יות
    0.47
    Πα
    0.46
    ﻱ
    0.44
    階
    0.43
    mouth
    0.42
    簡
    0.41
     र
    0.41
    תי
    0.41
    Aplic
    0.41
    對於
    0.40
    POSITIVE LOGITS
    ermak
    0.53
    azgo
    0.52
    aço
    0.51
     شرکت
    0.50
    ile
    0.50
     Zhang
    0.50
     oras
    0.50
     biomark
    0.49
    źdz
    0.49
     Jimenez
    0.49
    Act Density 0.000%

    No Known Activations