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

    Neuronpedia

    INDEX
    Explanations

    common phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ಕ
    0.51
    以上の
    0.50
    ೩
    0.50
    க்கு
    0.50
    棹
    0.49
    ゲル
    0.49
    ﺨ
    0.48
     Loại
    0.48
    曷
    0.48
    颱
    0.48
    POSITIVE LOGITS
     see
    0.59
    ↵↵
    0.49
    ेप
    0.48
     pry
    0.47
    oer
    0.47
    o
    0.46
      
    0.44
    。
    0.43
    ivity
    0.42
     See
    0.42
    Act Density 0.001%

    No Known Activations