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

    Neuronpedia

    INDEX
    Explanations

    entertainment expense

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     cientos
    1.07
     entornos
    0.97
    是要
    0.92
    κτη
    0.92
     propietarios
    0.92
     izquier
    0.90
    rictions
    0.89
     DME
    0.89
    тых
    0.88
     perfectamente
    0.87
    POSITIVE LOGITS
    ي
    0.95
    ोंग
    0.86
    ب
    0.82
    I
    0.79
    Გ
    0.76
    Singapore
    0.75
    Ciudad
    0.75
    (%
    0.75
    Ç
    0.75
    Ტ
    0.74
    Act Density 0.001%

    No Known Activations