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

    Neuronpedia

    INDEX
    Explanations

    possessive pronouns

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    PlainOldData
    -0.07
     septembre
    -0.07
    GetString
    -0.07
     TRAN
    -0.07
     تحص
    -0.07
    ►
    -0.06
    /**↵↵
    -0.06
     Shelley
    -0.06
     ساخت
    -0.06
     язы
    -0.06
    POSITIVE LOGITS
    Ign
    0.07
    zdy
    0.06
     控
    0.06
     Competitive
    0.06
     Fancy
    0.06
     Annie
    0.06
    -Christian
    0.06
    aru
    0.06
     Granted
    0.06
    단
    0.06
    Act Density 0.005%

    No Known Activations