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

    Neuronpedia

    INDEX
    Explanations

    proactive care

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     aleg
    0.81
     misappropri
    0.77
     usur
    0.75
     parámetros
    0.73
     nub
    0.71
     improper
    0.71
     argument
    0.70
     iri
    0.70
     reporter
    0.69
     popula
    0.68
    POSITIVE LOGITS
    nými
    0.83
    Yeni
    0.80
    x
    0.77
     우리는
    0.75
    Imagenes
    0.73
     Gracias
    0.73
    nesi
    0.73
    Jug
    0.72
    cology
    0.70
    Ends
    0.70
    Act Density 0.049%

    No Known Activations