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

    Neuronpedia

    INDEX
    Explanations

    locally or driving

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     due
    0.50
     zarówno
    0.46
     Amsterdam
    0.44
    c
    0.43
     iff
    0.43
     Arrays
    0.43
     both
    0.43
     whereas
    0.43
     Claims
    0.42
    brows
    0.41
    POSITIVE LOGITS
     త
    0.47
     الأكثر
    0.46
     клини
    0.46
     километров
    0.46
    ៦
    0.45
     algoritmo
    0.45
     تد
    0.44
    ielleicht
    0.44
    嚇
    0.44
    恐怖
    0.44
    Act Density 0.004%

    No Known Activations