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
    CNc
    0.61
     обратить
    0.56
    ormais
    0.54
    द्रा
    0.53
    urz
    0.52
    зон
    0.52
    ám
    0.51
    長時間
    0.50
    ောင်း
    0.50
     නිෂ්
    0.50
    POSITIVE LOGITS
     first
    6.02
    first
    5.59
     primeira
    4.97
     eerste
    4.79
     første
    4.74
     ersten
    4.72
     erste
    4.66
    First
    4.64
     primeiro
    4.63
     första
    4.59
    Act Density 0.763%

    No Known Activations