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

    Neuronpedia

    INDEX
    Explanations

    new tab

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     çoc
    0.83
     fête
    0.80
     criança
    0.80
     dépôt
    0.79
     récit
    0.79
     justiça
    0.79
     çocuk
    0.77
     cadeira
    0.77
     saúde
    0.76
    )²
    0.76
    POSITIVE LOGITS
    ्स
    0.91
    وده
    0.70
    ор
    0.69
    ITH
    0.68
    ARM
    0.68
    цем
    0.68
    サリー
    0.68
    ymph
    0.66
    INET
    0.66
    า
    0.65
    Act Density 11.352%

    No Known Activations