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

    Neuronpedia

    INDEX
    Explanations

    pirate and subsequent terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    1
    0.88
    ;
    0.81
    2
    0.79
    ان
    0.75
    an
    0.74
    ول
    0.74
    ل
    0.73
    기
    0.73
     आय
    0.71
    !
    0.71
    POSITIVE LOGITS
    ཎ
    0.67
    戞
    0.66
    手法
    0.62
    。「
    0.61
    とても
    0.61
    മാര്‍
    0.59
    勮
    0.59
    盛り
    0.59
    含む
    0.59
     হওয়
    0.58
    Act Density 0.001%

    No Known Activations