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

    Neuronpedia

    INDEX
    Explanations

    projects, frontier, pricing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    чности
    0.41
    મુ
    0.39
    MatchType
    0.38
     મુ
    0.38
     കേ
    0.38
    лізу
    0.37
    കേ
    0.36
    萘
    0.36
    に合わせて
    0.36
    рих
    0.36
    POSITIVE LOGITS
    ônia
    0.38
    onz
    0.38
     Bez
    0.37
     disb
    0.37
     fiscale
    0.37
    &
    0.37
    inii
    0.36
    izarro
    0.35
     ticketing
    0.35
     Promotions
    0.35
    Act Density 0.000%

    No Known Activations