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

    Neuronpedia

    INDEX
    Explanations

    by example or with client

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     pecado
    0.44
    尼亚克
    0.38
    бовать
    0.38
    TabData
    0.37
     cuero
    0.37
     بو
    0.36
     ediyoruz
    0.36
     parallèle
    0.36
    %)$
    0.36
     vuoi
    0.36
    POSITIVE LOGITS
     Ms
    0.61
     Mrs
    0.54
     Mr
    0.52
     Debbie
    0.52
     Sharon
    0.50
    Mrs
    0.48
     Julie
    0.47
    Ms
    0.46
     Sanjay
    0.46
     Sergey
    0.46
    Act Density 0.000%

    No Known Activations