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

    Neuronpedia

    INDEX
    Explanations

    historical context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     marks
    0.49
     taxes
    0.48
    ing
    0.48
     on
    0.47
     practicality
    0.47
     shelves
    0.46
     rarer
    0.46
    ilder
    0.45
    +
    0.45
    稒
    0.45
    POSITIVE LOGITS
    耘
    0.52
     selama
    0.45
    CUSS
    0.44
     Católica
    0.43
    पेयी
    0.43
     チェック
    0.43
     子
    0.43
    諒
    0.43
    ﺲ
    0.43
     軍
    0.42
    Act Density 0.000%

    No Known Activations