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

    Neuronpedia

    INDEX
    Explanations

    include or included

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ganas
    0.52
     finite
    0.50
    atorics
    0.50
    )
    0.50
     haz
    0.50
     Haz
    0.50
    状態
    0.50
     vendo
    0.50
     brillant
    0.50
     and
    0.49
    POSITIVE LOGITS
     Included
    0.97
    included
    0.94
     included
    0.91
     nelle
    0.89
     inclusion
    0.88
     součástí
    0.87
    inclusion
    0.85
     शामिल
    0.85
    ្នុង
    0.85
    添加到
    0.85
    Act Density 0.628%

    No Known Activations