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

    Neuronpedia

    INDEX
    Explanations

    owner selling property

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    za
    0.62
    ering
    0.59
    ando
    0.58
    alis
    0.56
    bid
    0.56
    𝙜
    0.55
    of
    0.54
    ibri
    0.54
    cbc
    0.52
    bier
    0.52
    POSITIVE LOGITS
    は
    0.70
    是
    0.64
     atteint
    0.63
    는
    0.63
     Maler
    0.62
     مالک
    0.61
    порт
    0.61
     Projeto
    0.61
     मैनेजमेंट
    0.60
    మన్
    0.59
    Act Density 0.011%

    No Known Activations