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

    Neuronpedia

    INDEX
    Explanations

    colab cell

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    '
    1.09
    ’
    0.85
    .'
    0.73
    getCql
    0.70
    '،
    0.67
     bismuth
    0.66
    gameField
    0.66
     थियो
    0.65
     sulfide
    0.64
     crystallography
    0.64
    POSITIVE LOGITS
     []:
    0.88
    ية
    0.88
    ę
    0.81
    د
    0.80
    مي
    0.76
    ী
    0.76
     براي
    0.75
    కి
    0.75
    de
    0.74
    يل
    0.71
    Act Density 0.004%

    No Known Activations