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

    Neuronpedia

    INDEX
    Explanations

    market in

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ى
    0.57
    。
    0.55
    л
    0.55
    æ
    0.55
    izable
    0.53
    tl
    0.52
    uses
    0.51
    nb
    0.51
    tv
    0.49
    sms
    0.49
    POSITIVE LOGITS
    ོང་
    0.56
     ໃນ
    0.54
     ຊ
    0.51
     haremos
    0.51
     ແມ່ນ
    0.50
     göstere
    0.50
    客厅
    0.50
     kõik
    0.50
     ನಾವು
    0.49
    UGHT
    0.49
    Act Density 0.000%

    No Known Activations