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

    Neuronpedia

    INDEX
    Explanations

    BL

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    廙
    -0.07
    羱
    -0.07
    ἔ
    -0.07
    猷
    -0.07
    🚜
    -0.07
     t�
    -0.07
     yaw
    -0.07
    筇
    -0.07
    xffff
    -0.07
     ipad
    -0.07
    POSITIVE LOGITS
    可以获得
    0.08
     characterization
    0.08
    备份
    0.07
    -effective
    0.07
     denying
    0.07
     restrained
    0.07
    的好
    0.07
    몹
    0.07
    (best
    0.07
     prec
    0.06
    Act Density 0.002%

    No Known Activations