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

    Neuronpedia

    INDEX
    Explanations

    companies and businesses

    np_acts-logits-general · gemini-2.5-flash-lite

    business and organization

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    с
    0.52
    .
    0.50
    。
    0.47
     is
    0.45
     be
    0.44
     it
    0.44
     。
    0.43
     它
    0.43
    اي
    0.43
    .。
    0.42
    POSITIVE LOGITS
    ir
    0.64
    im
    0.53
    ill
    0.51
    il
    0.50
    ad
    0.49
    ار
    0.48
    ine
    0.47
    induced
    0.47
    ar
    0.46
    ap
    0.44
    Act Density 3.089%

    No Known Activations