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

    Neuronpedia

    INDEX
    Explanations

    advice and requests

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ation
    0.47
    ights
    0.46
    ierd
    0.46
    isering
    0.45
    ails
    0.45
    asjon
    0.45
    ys
    0.44
    ższ
    0.43
    ings
    0.43
    ate
    0.43
    POSITIVE LOGITS
     mensagem
    0.54
     message
    0.52
     choir
    0.52
     pesan
    0.52
     lingerie
    0.50
     mesaj
    0.50
     sexu
    0.49
     const
    0.48
     neutral
    0.48
     petitioners
    0.47
    Act Density 0.000%

    No Known Activations