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

    Neuronpedia

    INDEX
    Explanations

    one-on-one

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    cpp
    -0.07
    测
    -0.07
    评定
    -0.07
    atoes
    -0.06
     che
    -0.06
    -data
    -0.06
    なのだ
    -0.06
    Education
    -0.06
    ND
    -0.06
     chilly
    -0.06
    POSITIVE LOGITS
    GenericType
    0.07
     exited
    0.07
    >/<
    0.06
    剜
    0.06
    ออกจาก
    0.06
    �
    0.06
     Этот
    0.06
    plemented
    0.06
     winger
    0.06
     fue
    0.06
    Act Density 0.003%

    No Known Activations