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

    Neuronpedia

    INDEX
    Explanations

    legal amendments

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    byn
    -0.08
     suck
    -0.07
    汾
    -0.07
    蕙
    -0.07
    において
    -0.07
    /umd
    -0.07
    _categorical
    -0.07
    奚
    -0.07
    垂
    -0.07
    =''):↵
    -0.06
    POSITIVE LOGITS
    三点
    0.07
     transport
    0.07
     linker
    0.07
     Exploration
    0.07
    стат
    0.07
    注册
    0.06
     three
    0.06
     bền
    0.06
    跨越
    0.06
    �
    0.06
    Act Density 0.011%

    No Known Activations