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

    Neuronpedia

    INDEX
    Explanations

    final result or output

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ChangeNotifier
    0.35
     cleverly
    0.33
    ರಿಕ
    0.32
    லைக்
    0.32
    ڳ
    0.32
    èdent
    0.31
    ⚔
    0.31
    ঙ্গিক
    0.31
    ียม
    0.31
     wisely
    0.30
    POSITIVE LOGITS
     resulting
    1.89
     결과
    1.84
     result
    1.81
    結果
    1.76
     résultat
    1.72
    resulting
    1.71
    结果
    1.70
     resultante
    1.70
     output
    1.66
     resultant
    1.66
    Act Density 0.077%

    No Known Activations