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

    Neuronpedia

    INDEX
    Explanations

    lists alternatives or choices

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     apl
    0.84
     mill
    0.77
     multi
    0.76
     sens
    0.75
     discerning
    0.74
     biz
    0.74
     semi
    0.74
     monochrome
    0.73
     sublim
    0.72
     brewing
    0.72
    POSITIVE LOGITS
    וֹ
    1.00
     અથવા
    0.92
     ಅಥವಾ
    0.89
     или
    0.88
     ወይም
    0.88
    ሳሌ
    0.87
    や
    0.87
    或
    0.86
    或者
    0.86
    ină
    0.86
    Act Density 0.001%

    No Known Activations