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

    Neuronpedia

    INDEX
    Explanations

    Code related to loss

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ，与
    -0.08
    定义
    -0.08
     эми
    -0.08
    将
    -0.07
     stereotype
    -0.07
    与
    -0.07
    确定
    -0.07
     maß
    -0.07
     JSON
    -0.07
     将
    -0.07
    POSITIVE LOGITS
    progress
    0.11
    _PROGRESS
    0.11
    .progress
    0.11
     evolución
    0.11
     progrès
    0.10
    ighth
    0.10
     evolução
    0.10
    _progress
    0.10
     glimps
    0.10
    	progress
    0.10
    Act Density 0.002%

    No Known Activations