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

    Neuronpedia

    INDEX
    Explanations

    beyond just

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    passion
    0.75
    leaflet
    0.74
    Вот
    0.73
    ্পনিক
    0.69
    Suitable
    0.69
    ів
    0.69
    poem
    0.68
    infected
    0.67
    izabeth
    0.67
    Ah
    0.66
    POSITIVE LOGITS
    ঞ্জ
    0.86
     importantly
    0.79
    बीन
    0.74
    ेक्स
    0.74
     jiné
    0.73
    enze
    0.73
    ு
    0.71
    erweise
    0.71
     cale
    0.71
    єд
    0.70
    Act Density 0.161%

    No Known Activations