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

    Neuronpedia

    INDEX
    Explanations

    multilingual text fragments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Liverpool
    0.63
     Fibonacci
    0.63
     tall
    0.62
     later
    0.61
     could
    0.61
     half
    0.59
     postwar
    0.58
     X
    0.57
     highs
    0.57
     Baroque
    0.57
    POSITIVE LOGITS
    льника
    0.70
    ให้น
    0.69
    偈
    0.66
    抠
    0.64
    attiyam
    0.60
    服务
    0.59
    くて
    0.58
    邹
    0.58
    їв
    0.57
    ение
    0.57
    Act Density 0.032%

    No Known Activations