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

    Neuronpedia

    INDEX
    Explanations

    check again in time

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Ỳ
    -1.02
    chtete
    -0.88
     koleksi
    -0.87
    Quickly
    -0.86
     hairdryer
    -0.86
    гән
    -0.85
    Tant
    -0.84
     podró
    -0.83
     Truy
    -0.82
     douleur
    -0.82
    POSITIVE LOGITS
     maintain
    0.99
     monthly
    0.96
     maintained
    0.93
     continua
    0.93
     frequency
    0.93
     next
    0.92
     intervals
    0.92
     interval
    0.92
     continues
    0.90
     maintaining
    0.88
    Act Density 0.011%

    No Known Activations