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

    Neuronpedia

    INDEX
    Explanations

    the followed by capitalized words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     napkins
    0.67
     ці
    0.67
     без
    0.66
     piercings
    0.62
    <unused702>
    0.62
     சரியான
    0.61
     исти
    0.60
     сме
    0.60
     ст
    0.60
    ഹ്ലാദ
    0.59
    POSITIVE LOGITS
    la
    0.60
    Om
    0.57
    landet
    0.55
    ln
    0.55
     rodzaj
    0.55
    ุ
    0.54
    Older
    0.53
    t
    0.53
    td
    0.53
    the
    0.52
    Act Density 0.705%

    No Known Activations