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

    Neuronpedia

    INDEX
    Explanations

    explaining why

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     devs
    0.51
     Tz
    0.49
     richting
    0.46
    今日も
    0.46
    އ
    0.45
    ພວກ
    0.45
     Vocal
    0.45
     ഫ
    0.45
     Besuch
    0.44
     després
    0.44
    POSITIVE LOGITS
    cessing
    0.55
    ancy
    0.49
    graduation
    0.46
    evening
    0.46
    fa
    0.44
    cienza
    0.44
    fly
    0.43
    ^{-}
    0.43
    lock
    0.43
    pisah
    0.43
    Act Density 0.011%

    No Known Activations