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

    Neuronpedia

    INDEX
    Explanations

    Words with various suffixes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _lane
    -0.07
     वह
    -0.07
     设
    -0.06
    respond
    -0.06
    kili
    -0.06
     DAG
    -0.06
    ізнес
    -0.06
     初始化
    -0.06
    	N
    -0.06
    ateral
    -0.06
    POSITIVE LOGITS
    AppState
    0.07
    광역시
    0.07
    _point
    0.06
    :event
    0.06
     acl
    0.06
     cherished
    0.06
     courageous
    0.06
    [:
    0.06
    _pedido
    0.06
     gut
    0.06
    Act Density 0.028%

    No Known Activations