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

    Neuronpedia

    INDEX
    Explanations

    apostrophe

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    殄
    -0.08
    疑难
    -0.07
     negligible
    -0.07
    短视频
    -0.07
    provider
    -0.07
    parison
    -0.07
    <Game
    -0.07
    镃
    -0.07
    �
    -0.06
    -shared
    -0.06
    POSITIVE LOGITS
    חברתי
    0.07
    acz
    0.07
    Te
    0.07
    into
    0.07
    Shar
    0.07
    usc
    0.07
     conditioner
    0.06
    squ
    0.06
    姿势
    0.06
     jusqu
    0.06
    Act Density 0.001%

    No Known Activations