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

    Neuronpedia

    INDEX
    Explanations

    most followed by a quality

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     I
    0.61
     a
    0.59
    에
    0.50
     on
    0.50
     anesthet
    0.49
    리
    0.49
    २
    0.47
    AA
    0.47
     maquill
    0.46
     operações
    0.46
    POSITIVE LOGITS
    t
    0.86
    most
    0.68
    likely
    0.66
     happiest
    0.64
     cleanest
    0.64
    tti
    0.61
    largest
    0.60
     healthiest
    0.59
    ния
    0.57
     nhất
    0.57
    Act Density 0.101%

    No Known Activations