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

    Neuronpedia

    INDEX
    Explanations

    The

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Thai
    -0.08
    depart
    -0.07
     orc
    -0.07
     irony
    -0.07
    -operation
    -0.06
     sinks
    -0.06
    jit
    -0.06
    Thai
    -0.06
     Kahn
    -0.06
    shan
    -0.06
    POSITIVE LOGITS
     nhanh
    0.07
    (/^\
    0.06
    次数
    0.06
    �
    0.06
     polov
    0.06
     хотел
    0.06
    นท
    0.06
     Player
    0.06
     코
    0.06
    Compar
    0.06
    Act Density 0.016%

    No Known Activations