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

    Neuronpedia

    INDEX
    Explanations

    Russian boasting and Spanish uploads

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ifying
    1.18
    izing
    1.07
    ierung
    1.06
    ablement
    0.98
    ishment
    0.96
    owanie
    0.93
    leyici
    0.91
    idation
    0.91
    ation
    0.90
    ające
    0.90
    POSITIVE LOGITS
     Humans
    0.79
     Người
    0.70
     Romans
    0.69
     Soup
    0.68
     ventured
    0.67
     Historical
    0.66
     Spirit
    0.65
     Approaches
    0.65
     Strugg
    0.65
     Faces
    0.65
    Act Density 0.040%

    No Known Activations