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

    Neuronpedia

    INDEX
    Explanations

    variables and placeholders

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    кры
    0.46
    сты
    0.46
    зом
    0.46
    вый
    0.45
    CTS
    0.45
    jars
    0.44
    chord
    0.42
    ться
    0.42
    гла
    0.42
    罪
    0.41
    POSITIVE LOGITS
    Ix
    0.66
    ilized
    0.49
     خ
    0.47
     لكن
    0.47
    Ii
    0.46
    篓
    0.46
    Ich
    0.45
    Rebecca
    0.45
     พี่
    0.45
    Ih
    0.44
    Act Density 0.003%

    No Known Activations