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

    Neuronpedia

    INDEX
    Explanations

    know how to handle

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Tuscany
    0.54
     человеку
    0.54
     पर्यवे
    0.52
     შეგიძლიათ
    0.51
    police
    0.50
     Consultado
    0.49
    dataLayer
    0.48
     policewomen
    0.48
    )})
    0.48
     Rajasthan
    0.48
    POSITIVE LOGITS
     i
    0.54
     tros
    0.52
     r
    0.51
    ir
    0.50
    Lett
    0.50
    Providing
    0.50
    Sehr
    0.49
     s
    0.47
     bake
    0.47
     très
    0.46
    Act Density 0.000%

    No Known Activations