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

    Neuronpedia

    INDEX
    Explanations

    attached link copy screenshot photographing pages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     initiale
    0.71
     jõ
    0.67
    äg
    0.66
    ależy
    0.66
     przes
    0.64
    níky
    0.63
     Porém
    0.63
    人了
    0.63
    érant
    0.62
    عي
    0.62
    POSITIVE LOGITS
     마련
    0.61
     Acta
    0.57
    Memento
    0.56
     Affordable
    0.55
     recuerdos
    0.55
    om
    0.55
     vial
    0.54
    <unused2197>
    0.53
    strftime
    0.52
     neoliberal
    0.52
    Act Density 0.025%

    No Known Activations