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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     �
    -0.07
    warts
    -0.07
    투
    -0.07
    ERGY
    -0.07
    rift
    -0.06
    itus
    -0.06
    dag
    -0.06
     Mock
    -0.06
    �
    -0.06
     جلو
    -0.06
    POSITIVE LOGITS
    出品
    0.07
     tổn
    0.06
    _DL
    0.06
     Tes
    0.06
     har
    0.06
     aftermarket
    0.06
    跌
    0.06
    URAL
    0.06
     },↵↵↵
    0.06
    -instagram
    0.06
    Act Density 0.138%

    No Known Activations