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

    Neuronpedia

    INDEX
    Explanations

    code/data

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     návr
    -0.07
     consensus
    -0.06
    filePath
    -0.06
    ."""↵↵
    -0.06
    national
    -0.06
    agement
    -0.06
    tile
    -0.06
    องค
    -0.06
     Essentially
    -0.06
     comprom
    -0.06
    POSITIVE LOGITS
     başk
    0.06
    quete
    0.06
    .Absolute
    0.06
     EXPORT
    0.06
     voks
    0.06
    sj
    0.06
    ыл
    0.06
     crashed
    0.06
    ávající
    0.06
     polít
    0.06
    Act Density 4.117%

    No Known Activations