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

    Neuronpedia

    INDEX
    Explanations

    byte / character data types

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    복
    -0.07
     exclude
    -0.06
    ᴜ
    -0.06
     �
    -0.06
    �
    -0.06
    尽
    -0.06
     cita
    -0.06
     subscribe
    -0.06
    _train
    -0.06
    lectual
    -0.06
    POSITIVE LOGITS
    县公安局
    0.07
     relay
    0.07
    Pair
    0.07
    לכת
    0.07
    _px
    0.07
     Belly
    0.07
     blir
    0.07
    تاريخ
    0.07
    몫
    0.07
     }}>
    0.06
    Act Density 0.038%

    No Known Activations