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

    Neuronpedia

    INDEX
    Explanations

    sequential module

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Defender
    0.79
    kitty
    0.76
    apsack
    0.76
     Defender
    0.74
     Deficiency
    0.73
     Valletta
    0.73
    છી
    0.73
     виду
    0.71
     нескольких
    0.71
     Diversity
    0.70
    POSITIVE LOGITS
     justices
    0.80
     đảng
    0.80
    起来
    0.78
    踊
    0.77
    ולם
    0.76
    ্যালি
    0.74
    されている
    0.73
     wyniki
    0.73
    演技
    0.73
    ብሰ
    0.71
    Act Density 0.000%

    No Known Activations