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

    Neuronpedia

    INDEX
    Explanations

    court appeals

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    数字经济
    -0.08
     mov
    -0.07
    tries
    -0.07
    edores
    -0.07
     tấn
    -0.07
    ארצות
    -0.07
     leurs
    -0.06
    pk
    -0.06
    택
    -0.06
     Garden
    -0.06
    POSITIVE LOGITS
    感到
    0.07
     对
    0.07
    不懂
    0.07
     alteration
    0.07
    깟
    0.07
     documentation
    0.07
    感
    0.06
     ArgumentException
    0.06
    стал
    0.06
    omat
    0.06
    Act Density 0.001%

    No Known Activations