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

    Neuronpedia

    INDEX
    Explanations

    "entitled"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     etch
    0.67
     cámara
    0.64
     phoned
    0.64
    st
    0.62
    旧
    0.61
    ই
    0.60
    textAlign
    0.60
    icu
    0.59
    م
    0.58
     empec
    0.58
    POSITIVE LOGITS
    с
    0.86
     Paryayvachi
    0.67
    ت
    0.65
    ла
    0.64
    //{
    0.63
    फेसर
    0.61
     Pythagorean
    0.60
    оти
    0.59
    zione
    0.57
    젝트
    0.56
    Act Density 0.002%

    No Known Activations