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

    Neuronpedia

    INDEX
    Explanations

    email services or forms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Sí
    0.98
     Zwischen
    0.92
    eper
    0.86
     গিয়া
    0.81
     Verbindung
    0.79
     Beneficial
    0.79
     diferença
    0.79
     Nuestro
    0.78
     aí
    0.78
     کریں۔
    0.78
    POSITIVE LOGITS
    ל
    1.04
    न
    1.03
    ان
    1.01
    我
    0.96
     tunnels
    0.86
    ра
    0.82
    ри
    0.82
    ли
    0.81
     helicopters
    0.77
    на
    0.75
    Act Density 0.001%

    No Known Activations