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

    Neuronpedia

    INDEX
    Explanations

    descriptive adjectives followed by nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     известные
    0.38
     Cambridge
    0.38
     economic
    0.38
    archa
    0.37
     ලෙස
    0.36
     directamente
    0.36
     宋
    0.36
     shallow
    0.36
     hitherto
    0.36
     johnson
    0.36
    POSITIVE LOGITS
    realistic
    0.50
    Realistic
    0.49
    Чтобы
    0.47
     simulates
    0.45
     realistic
    0.44
    Similar
    0.44
     لتح
    0.43
    sized
    0.42
    Multiple
    0.42
     Realistic
    0.42
    Act Density 0.004%

    No Known Activations