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

    Neuronpedia

    INDEX
    Explanations

    but

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     نسب
    -0.07
     kvinder
    -0.07
     레이
    -0.07
    orris
    -0.07
    (Some
    -0.07
     corrid
    -0.07
     х
    -0.06
    ureen
    -0.06
     thậm
    -0.06
    seven
    -0.06
    POSITIVE LOGITS
     relocated
    0.07
    ._↵
    0.06
     restarting
    0.06
     tactical
    0.06
     journals
    0.06
    ॉ
    0.06
     TFT
    0.06
    LEFT
    0.06
    ').'</
    0.06
    system
    0.06
    Act Density 0.000%

    No Known Activations