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

    Neuronpedia

    INDEX
    Explanations

    function calls or definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    amps
    1.11
     화학
    1.10
     안
    1.08
     언제
    1.06
     빈
    1.05
     избе
    1.03
    휘
    1.01
     Wheaton
    1.00
    럇
    1.00
     처음
    1.00
    POSITIVE LOGITS
     familiares
    1.18
    it
    1.01
    cı
    1.00
     audiov
    1.00
     يست
    0.99
    ामध्ये
    0.99
    рати
    0.98
     দর্শন
    0.97
    देख
    0.97
    Пере
    0.95
    Act Density 0.000%

    No Known Activations