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

    Neuronpedia

    INDEX
    Explanations

    can't be beat!

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    послед
    0.46
     аба
    0.45
     УК
    0.45
    回家
    0.45
     पूर्णा
    0.44
    雎
    0.44
     ఆగ
    0.44
     সেনান
    0.44
     όχι
    0.43
     beng
    0.43
    POSITIVE LOGITS
     trusted
    0.66
     timet
    0.64
     teamTable
    0.63
    PT
    0.62
     timer
    0.61
    ни
    0.61
    dT
    0.60
    Ｔ
    0.60
    IT
    0.60
    <0x0D>
    0.59
    Act Density 0.028%

    No Known Activations