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

    Neuronpedia

    INDEX
    Explanations

    kirkwood

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    꿈
    0.41
    ‌ای
    0.41
    ℚ
    0.40
     setSelected
    0.39
    翊
    0.38
    贻
    0.38
    峠
    0.38
    創造
    0.38
    धी
    0.38
    روز
    0.38
    POSITIVE LOGITS
     kir
    0.52
     I
    0.48
    Kir
    0.46
     KIR
    0.43
     chir
    0.43
     Ch
    0.42
     Kir
    0.42
     Kirk
    0.39
    VP
    0.39
     L
    0.39
    Act Density 0.000%

    No Known Activations