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

    Neuronpedia

    INDEX
    Explanations

    tabular data headers or lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     enjoyed
    0.85
     immuno
    0.83
    dns
    0.82
     Ironically
    0.82
     seconde
    0.81
     Ayn
    0.81
     deux
    0.80
    нус
    0.79
    inction
    0.79
     پیچھے
    0.79
    POSITIVE LOGITS
     წყ
    0.78
    час
    0.75
    FFIC
    0.74
     routes
    0.74
    থায়
    0.71
    hline
    0.70
    <caption>
    0.70
    burne
    0.69
     gele
    0.69
    ways
    0.68
    Act Density 0.070%

    No Known Activations