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

    Neuronpedia

    INDEX
    Explanations

    common

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    轲
    -0.07
     Ang
    -0.07
    (dw
    -0.07
    Aug
    -0.07
    下次
    -0.07
    �
    -0.07
    ност
    -0.06
    .MiddleCenter
    -0.06
     verify
    -0.06
    -seven
    -0.06
    POSITIVE LOGITS
     películ
    0.07
    罕见
    0.07
     lithium
    0.07
    房子
    0.07
    崡
    0.06
     Charg
    0.06
    وني
    0.06
     crianças
    0.06
     Cộng
    0.06
    史
    0.06
    Act Density 0.033%

    No Known Activations