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

    Neuronpedia

    INDEX
    Explanations

    Comments

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     oz
    -0.08
    ENCH
    -0.07
    ɜ
    -0.07
     dela
    -0.06
     dislikes
    -0.06
     CHAPTER
    -0.06
    棹
    -0.06
    绱
    -0.06
     mange
    -0.06
    ｧ
    -0.06
    POSITIVE LOGITS
    라면
    0.09
    込む
    0.08
     Stalin
    0.07
    icism
    0.07
    _instances
    0.07
     Beckham
    0.07
    (Str
    0.07
    пр
    0.07
    (script
    0.07
    祸
    0.07
    Act Density 0.003%

    No Known Activations