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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     rings
    -0.08
    �
    -0.08
    樱
    -0.08
    Пр
    -0.07
    扇
    -0.07
     rasp
    -0.07
    .multipart
    -0.07
    )}.
    -0.07
    不需要
    -0.07
     *.
    -0.07
    POSITIVE LOGITS
    (Code
    0.07
     Ain
    0.07
     Vox
    0.06
     pneum
    0.06
    voor
    0.06
    posing
    0.06
    薪资
    0.06
     principalColumn
    0.06
    amaha
    0.06
    腿部
    0.06
    Act Density 0.083%

    No Known Activations