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

    Neuronpedia

    INDEX
    Explanations

    Legal claims and arguments

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    전자
    -0.08
    (gt
    -0.08
    .Dispose
    -0.07
     DV
    -0.07
     CCTV
    -0.07
    孵
    -0.07
    /top
    -0.07
     técnico
    -0.07
     próp
    -0.07
     thịt
    -0.07
    POSITIVE LOGITS
    王
    0.07
    ham
    0.07
     followers
    0.07
    🇬
    0.07
     nomination
    0.06
    痛
    0.06
    .movie
    0.06
    Named
    0.06
    Acknowled
    0.06
    美国总统
    0.06
    Act Density 0.023%

    No Known Activations