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

    Neuronpedia

    INDEX
    Explanations

    floor

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    诊疗
    -0.07
    第二节
    -0.07
     advises
    -0.07
    เ
    -0.07
    lli
    -0.07
     thought
    -0.07
     mcc
    -0.07
     sai
    -0.07
     disse
    -0.07
    \xff
    -0.07
    POSITIVE LOGITS
    -air
    0.09
    طائر
    0.08
     flower
    0.07
    婊
    0.07
    -map
    0.07
     cupboard
    0.07
    Ready
    0.07
    ◘
    0.07
    这样一来
    0.07
    RefreshLayout
    0.07
    Act Density 0.005%

    No Known Activations