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

    Neuronpedia

    INDEX
    Explanations

    pandas pd

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     וא
    1.52
     cotid
    1.43
    𝘤
    1.27
     sélectionnez
    1.24
    𝘭
    1.23
    benzoimidazole
    1.22
    𝘱
    1.22
    codewords
    1.20
    ඃ
    1.19
    𝘶
    1.17
    POSITIVE LOGITS
    an
    1.31
    स
    1.19
    ́n
    1.17
    ah
    1.16
    न
    1.15
    ية
    1.13
    ن
    1.13
    ing
    1.08
    ate
    1.05
    és
    1.05
    Act Density 0.004%

    No Known Activations