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

    Neuronpedia

    INDEX
    Explanations

    ability

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    幻想
    -0.07
    单位
    -0.07
     r
    -0.07
    run
    -0.07
    住户
    -0.06
    come
    -0.06
    returns
    -0.06
     forcing
    -0.06
    追究
    -0.06
     hus
    -0.06
    POSITIVE LOGITS
    游戏装备
    0.07
    瑔
    0.07
    ɐ
    0.07
     seals
    0.07
     contraception
    0.06
    _sock
    0.06
    :)])
    0.06
     Firstly
    0.06
    strconv
    0.06
    .flex
    0.06
    Act Density 0.001%

    No Known Activations