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

    Neuronpedia

    INDEX
    Explanations

    Negations and conditional instructions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    吸引
    -0.07
    דיון
    -0.07
    おります
    -0.07
     workplace
    -0.07
    .getLength
    -0.07
     nomine
    -0.07
     advert
    -0.06
    打扰
    -0.06
    aramel
    -0.06
    价值
    -0.06
    POSITIVE LOGITS
    uish
    0.07
    SS
    0.07
    씽
    0.07
    (prefix
    0.06
     prefers
    0.06
    _series
    0.06
     kịch
    0.06
    这套
    0.06
     stripping
    0.06
     projecting
    0.06
    Act Density 0.034%

    No Known Activations