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

    Neuronpedia

    INDEX
    Explanations

    on _

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     retribution
    0.40
    াতাড়ি
    0.39
    URNS
    0.38
    รียม
    0.38
    ULA
    0.38
     prawdopod
    0.38
    צע
    0.37
    ！！
    0.37
     температур
    0.37
    APPENDIX
    0.37
    POSITIVE LOGITS
     On
    0.77
     ON
    0.75
     behalf
    0.70
    slaught
    0.65
    mouseover
    0.58
     Oni
    0.58
    ward
    0.57
     demand
    0.57
     Он
    0.56
    ono
    0.54
    Act Density 0.016%

    No Known Activations