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

    Neuronpedia

    INDEX
    Explanations

    conversational introductory words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    il
    1.03
    ر
    0.99
     by
    0.93
    न
    0.92
    0
    0.91
    ad
    0.91
     a
    0.91
    ন
    0.91
    ૦
    0.86
    र
    0.85
    POSITIVE LOGITS
    с
    1.16
    .
    1.08
    ian
    1.05
    是
    1.00
    -
    0.99
    కు
    0.91
    公司
    0.89
    面
    0.88
    章
    0.87
    的关系
    0.86
    Act Density 0.000%

    No Known Activations