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

    Neuronpedia

    INDEX
    Explanations

    deals and offers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    us
    0.55
     hd
    0.51
    usin
    0.50
    usst
    0.49
     что
    0.49
    uana
    0.48
     يه
    0.46
    rah
    0.46
    itr
    0.46
    it
    0.46
    POSITIVE LOGITS
    徉
    0.51
     aktif
    0.46
    ั่ง
    0.46
     wildest
    0.44
    ValueLayout
    0.42
    繧
    0.42
    ƾ
    0.42
    牷
    0.42
     alcun
    0.41
     offerte
    0.41
    Act Density 0.000%

    No Known Activations