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

    Neuronpedia

    INDEX
    Explanations

    e

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    睛
    -0.07
    馒
    -0.07
    His
    -0.07
     ראש
    -0.07
     marvel
    -0.07
    土耳
    -0.07
     השלישי
    -0.07
    👪
    -0.06
     Morris
    -0.06
     quá
    -0.06
    POSITIVE LOGITS
    原本
    0.08
    另外
    0.08
    !"↵↵
    0.07
     tier
    0.07
    NOTE
    0.07
    Retention
    0.07
     {!
    0.07
    "
↵
    0.07
     OPERATION
    0.07
    stat
    0.06
    Act Density 0.005%

    No Known Activations