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

    Neuronpedia

    INDEX
    Explanations

    starts with B

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     боль
    2.19
     afirma
    2.09
    mainan
    1.88
     toa
    1.87
    om
    1.84
     большую
    1.84
     berapa
    1.80
     llama
    1.77
    ien
    1.77
    ري
    1.77
    POSITIVE LOGITS
     וב
    2.42
    hesda
    2.05
    碚
    2.02
     Boo
    1.87
     Beware
    1.86
    ื้อง
    1.86
     الاقوامی
    1.85
    Boo
    1.85
    ко
    1.84
    杷
    1.84
    Act Density 2.360%

    No Known Activations