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

    Neuronpedia

    INDEX
    Explanations

    size

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    izin
    -0.07
    _of
    -0.07
    かわ
    -0.06
    _radio
    -0.06
    789
    -0.06
    ค
    -0.06
    悉
    -0.06
     Raise
    -0.06
     LTD
    -0.06
    (data
    -0.06
    POSITIVE LOGITS
    ---------↵↵
    0.07
     busty
    0.07
     zby
    0.07
     ');
↵
    0.06
    aştır
    0.06
    ?"↵↵↵↵
    0.06
     ************************************************
    0.06
    ,},↵
    0.06
    ↵↵↵↵
    0.06
    “Our
    0.06
    Act Density 0.015%

    No Known Activations