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

    Neuronpedia

    INDEX
    Explanations

    programming code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Lig
    -0.07
     shed
    -0.07
    _product
    -0.07
     Guil
    -0.06
    婷
    -0.06
    Wil
    -0.06
    clusive
    -0.06
     reliable
    -0.06
    Wal
    -0.06
    艺术品
    -0.06
    POSITIVE LOGITS
    עונש
    0.07
     בעזרת
    0.07
    piar
    0.07
    ↼
    0.07
     giữa
    0.07
    女の
    0.07
     Bruins
    0.07
    췌
    0.07
     Diğer
    0.07
    跻身
    0.07
    Act Density 0.109%

    No Known Activations