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

    Neuronpedia

    INDEX
    Explanations

    Biographies

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _fence
    -0.08
    米饭
    -0.07
    一轮
    -0.07
    enance
    -0.07
    establish
    -0.07
     kings
    -0.07
     المسلم
    -0.07
     deals
    -0.07
    stable
    -0.07
     enabling
    -0.07
    POSITIVE LOGITS
     specialization
    0.08
    цен
    0.07
    ßer
    0.07
    .Url
    0.07
    週
    0.06
     Tâm
    0.06
    ţi
    0.06
    ㇾ
    0.06
     laten
    0.06
     컴퓨터
    0.06
    Act Density 0.015%

    No Known Activations