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

    Neuronpedia

    INDEX
    Explanations

    listing conjunction

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     For
    0.68
     And
    0.68
    $,
    0.61
     By
    0.60
    م
    0.59
     They
    0.57
    ्यारह
    0.56
     With
    0.55
     After
    0.55
     First
    0.54
    POSITIVE LOGITS
     sebagainya
    0.66
    _
    0.65
    romeda
    0.63
    {
    0.63
    RE
    0.61
    都是
    0.60
    DetailUI
    0.59
     технологі
    0.59
    RO
    0.58
    Have
    0.58
    Act Density 0.422%

    No Known Activations