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

    Neuronpedia

    INDEX
    Explanations

    point

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ế
    -0.08
    เย
    -0.07
    规矩
    -0.07
    ე
    -0.07
     Rück
    -0.07
     gór
    -0.07
    ده
    -0.07
     Essays
    -0.07
     eins
    -0.06
     ổn
    -0.06
    POSITIVE LOGITS
    sid
    0.08
    .PackageManager
    0.07
    __
    0.07
    RadioButton
    0.07
    ===
    0.07
    assed
    0.07
     Ph
    0.07
     רוצה
    0.06
     Pistol
    0.06
    (groupId
    0.06
    Act Density 0.004%

    No Known Activations