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

    Neuronpedia

    INDEX
    Explanations

    end of sentence descriptive words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     võib
    0.46
    然后再
    0.45
     chuva
    0.44
     écailles
    0.42
     bőr
    0.42
    <unused558>
    0.41
    <unused536>
    0.40
     jiné
    0.40
    ຂໍ້ມ
    0.40
     cárcel
    0.39
    POSITIVE LOGITS
     saker
    0.49
     (
    0.48
    ';
    0.47
    ";
    0.46
    )
    0.46
     multi
    0.46
     Humphrey
    0.44
    Int
    0.43
     Aragon
    0.43
    Z
    0.42
    Act Density 0.199%

    No Known Activations