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

    Neuronpedia

    INDEX
    Explanations

    curved

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     UNKNOWN
    -0.09
    在他
    -0.08
    (man
    -0.08
     Communities
    -0.08
     Secret
    -0.07
    上午
    -0.07
     Luna
    -0.07
    就是
    -0.07
    eway
    -0.07
    (bytes
    -0.07
    POSITIVE LOGITS
    acaktır
    0.08
    นาม
    0.07
    ест
    0.07
    �니다
    0.07
    耶�
    0.07
    욱
    0.07
    third
    0.07
     março
    0.07
    ılm
    0.06
    court
    0.06
    Act Density 0.013%

    No Known Activations