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

    Neuronpedia

    INDEX
    Explanations

    2

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -0.08
    מוש
    -0.07
    ישה
    -0.07
     DNS
    -0.07
     vague
    -0.07
    れる
    -0.07
    (dd
    -0.06
     Bh
    -0.06
    辆
    -0.06
     dislikes
    -0.06
    POSITIVE LOGITS
    精益
    0.08
    定律
    0.07
    二等奖
    0.07
     Scient
    0.07
     Locate
    0.06
     Schwartz
    0.06
     homer
    0.06
     ORM
    0.06
     onBindViewHolder
    0.06
    atsby
    0.06
    Act Density 0.054%

    No Known Activations