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

    Neuronpedia

    INDEX
    Explanations

    title followed by name

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Mr
    0.52
    Mrs
    0.50
    年轻
    0.50
    妇女
    0.49
    احمد
    0.49
    父親
    0.48
    先生
    0.48
     ಕರಿ
    0.48
     मियां
    0.48
     principalColumn
    0.48
    POSITIVE LOGITS
     (
    0.60
     from
    0.55
    ↵
    0.52
      
    0.51
    it
    0.50
     of
    0.50
     games
    0.50
    ul
    0.49
    st
    0.48
    er
    0.48
    Act Density 0.023%

    No Known Activations