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

    Neuronpedia

    INDEX
    Explanations

    such... so.

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     यात
    0.81
    こちらも
    0.79
     latter
    0.76
    ങ്ങളിലും
    0.73
     이건
    0.73
    Yep
    0.72
    これは
    0.69
    ಗಳಿಗೆ
    0.69
    ностей
    0.68
     قريب
    0.67
    POSITIVE LOGITS
     such
    5.10
    such
    4.32
     Such
    4.11
    Such
    4.08
     SUCH
    4.04
     so
    3.80
    如此
    3.56
     такой
    3.53
    這麼
    3.45
     så
    3.44
    Act Density 0.225%

    No Known Activations