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

    Neuronpedia

    INDEX
    Explanations

    benchmark

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Driven
    -0.08
    ጃ
    -0.08
    Vir
    -0.08
    Bond
    -0.07
     Spark
    -0.07
    ondrous
    -0.07
    &P
    -0.07
    绚丽
    -0.07
    versions
    -0.07
    vic
    -0.07
    POSITIVE LOGITS
    ꧈
    0.08
     Asians
    0.07
    مناقش
    0.07
     ArgumentException
    0.07
     בבק
    0.07
     rowData
    0.07
    乘客
    0.07
    'util
    0.07
     ila
    0.07
     Rajasthan
    0.07
    Act Density 0.004%

    No Known Activations