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

    Neuronpedia

    INDEX
    Explanations

    Instead of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ridiculed
    0.33
     Surname
    0.32
     Sereth
    0.31
     declinations
    0.30
     Galaxies
    0.30
     Declined
    0.30
     Cavaliers
    0.29
     blatantly
    0.29
     blatant
    0.29
     Deity
    0.29
    POSITIVE LOGITS
     você
    0.44
     infrastrukt
    0.43
     tenaga
    0.41
     तुम्ही
    0.40
     vous
    0.39
     menjel
    0.39
     menghadapi
    0.39
    เวลา
    0.38
     établissements
    0.38
    íte
    0.38
    Act Density 3.837%

    No Known Activations