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

    Neuronpedia

    INDEX
    Explanations

    outline what, option 1

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    РЕ
    2.17
    ן
    2.16
    ﺴ
    2.14
    ﺶ
    2.14
     tornando
    2.09
    ﺤ
    2.08
    ﯽ
    2.08
    ان
    2.00
    ﺘ
    2.00
    ﮏ
    1.98
    POSITIVE LOGITS
    राणिक
    2.14
    说
    2.09
    oretically
    1.95
     prilikom
    1.88
    e
    1.88
    ट
    1.86
    ︵
    1.84
    স
    1.80
     Wav
    1.78
     Fonts
    1.77
    Act Density 1.339%

    No Known Activations