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

    Neuronpedia

    INDEX
    Explanations

    as it returns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     in
    -1.87
     now
    -1.78
     then
    -1.74
     will
    -1.71
     often
    -1.70
     like
    -1.69
     when
    -1.68
     only
    -1.62
     or
    -1.57
     can
    -1.43
    POSITIVE LOGITS
     fleurs
    1.53
     нынеш
    1.51
     Jest
    1.48
    妩
    1.47
     jogadores
    1.45
     beaucoup
    1.42
     THOMAS
    1.41
    acknowled
    1.38
    tualmente
    1.35
    𓆏
    1.35
    Act Density 0.088%

    No Known Activations