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

    Neuronpedia

    INDEX
    Explanations

    woman yelling at cat

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     লঙ্ঘন
    0.51
    ᴠ
    0.41
    劭
    0.39
    হল
    0.38
     стрелецкой
    0.37
     отличие
    0.37
    ထုတ်
    0.37
    েরে
    0.37
    rcl
    0.36
     Modes
    0.36
    POSITIVE LOGITS
     consolid
    0.44
     Ched
    0.43
     mister
    0.41
     Caravan
    0.39
     jaguar
    0.39
     Chai
    0.38
    aniyati
    0.38
     deli
    0.37
     muffin
    0.37
     cheddar
    0.37
    Act Density 0.002%

    No Known Activations