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

    Neuronpedia

    INDEX
    Explanations

    public or support

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    feldt
    0.94
     montagne
    0.92
    ibilities
    0.90
    ibilidades
    0.90
    Versioning
    0.87
    gação
    0.87
    بیل
    0.85
    לחמת
    0.85
     edilen
    0.84
    خبار
    0.84
    POSITIVE LOGITS
     hat
    0.81
    <0x80>
    0.78
     pesky
    0.76
     Lovely
    0.74
     recital
    0.72
     Λ
    0.72
     تھیں۔
    0.69
     powdered
    0.69
     plaus
    0.69
     powdery
    0.69
    Act Density 0.001%

    No Known Activations