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

    Neuronpedia

    INDEX
    Explanations

    in various languages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ponder
    0.77
     factoring
    0.74
     incred
    0.74
     없음
    0.74
     whatnot
    0.73
     cheerleader
    0.73
     Parton
    0.72
     queer
    0.72
     bilater
    0.71
     stren
    0.70
    POSITIVE LOGITS
    에서
    2.71
     में
    2.57
     میں
    2.41
    에서도
    2.24
    에서는
    2.21
    において
    2.16
    లో
    2.15
    에서의
    2.11
    માં
    2.04
     ਵਿੱਚ
    2.02
    Act Density 0.068%

    No Known Activations