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

    Neuronpedia

    INDEX
    Explanations

    router

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ilor
    0.49
     ക്രിക്ക
    0.46
    ៤
    0.46
    ٣
    0.46
    ٤
    0.45
    ๔
    0.45
    ੪
    0.45
    があります
    0.45
    Е
    0.44
    Ⲕ
    0.44
    POSITIVE LOGITS
    ou
    0.62
    of
    0.55
    ור
    0.54
    imee
    0.49
    between
    0.47
    点
    0.46
     XOR
    0.45
    튕
    0.45
    ުރު
    0.44
     MPEG
    0.43
    Act Density 0.004%

    No Known Activations