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

    Neuronpedia

    INDEX
    Explanations

    what followed by a

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     타입
    0.54
     باہنی
    0.54
    ্দের
    0.49
     postérieur
    0.49
     查询
    0.49
     작업
    0.49
     найти
    0.49
     실행
    0.48
     típus
    0.48
    ysets
    0.48
    POSITIVE LOGITS
    8
    0.56
    4
    0.52
     and
    0.51
    ig
    0.50
     Tr
    0.50
     Brian
    0.49
     It
    0.49
     G
    0.48
     T
    0.48
    B
    0.46
    Act Density 0.000%

    No Known Activations