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

    Neuronpedia

    INDEX
    Explanations

    one or more

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    bourne
    0.40
    bim
    0.39
    being
    0.38
    essere
    0.38
    has
    0.37
    can
    0.37
    substring
    0.37
    <unused50>
    0.36
    display
    0.35
    causing
    0.35
    POSITIVE LOGITS
     மேற்பட்ட
    0.60
     more
    0.56
     preferably
    0.51
     ከዚያ
    0.51
     hơn
    0.50
    以上的
    0.47
     maybe
    0.43
     arguably
    0.43
     many
    0.43
     dozens
    0.43
    Act Density 0.030%

    No Known Activations