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

    Neuronpedia

    INDEX
    Explanations

    code characters

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    邹
    -0.07
    Hardware
    -0.07
     billionaire
    -0.07
    一瓶
    -0.07
    NBC
    -0.07
    Club
    -0.07
    optional
    -0.07
    Ars
    -0.07
    纯净
    -0.07
    뉴
    -0.06
    POSITIVE LOGITS
    न
    0.07
    所产生的
    0.06
    認識
    0.06
    .Anchor
    0.06
     officer
    0.06
     кров
    0.06
    .toObject
    0.06
     transform
    0.06
    _IN
    0.06
    솨
    0.06
    Act Density 0.093%

    No Known Activations