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

    Neuronpedia

    INDEX
    Explanations

    first

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     обратить
    0.58
    CNc
    0.56
    setcounter
    0.56
    urz
    0.54
    зон
    0.52
    ந்
    0.50
     உச்ச
    0.50
    unce
    0.48
    ेंजर
    0.48
    izante
    0.47
    POSITIVE LOGITS
     first
    5.76
    first
    5.32
     primeira
    4.78
     eerste
    4.64
     første
    4.61
     ersten
    4.57
     erste
    4.56
     первый
    4.45
     첫
    4.45
     första
    4.43
    Act Density 0.382%

    No Known Activations