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

    Neuronpedia

    INDEX
    Explanations

    connection issues

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    t
    0.97
    폭
    0.83
    yil
    0.77
     lamb
    0.75
    íram
    0.75
     Our
    0.74
    Our
    0.73
    doll
    0.73
     prosecuted
    0.71
     amikor
    0.71
    POSITIVE LOGITS
    ],//
    0.71
    を備
    0.71
    เสื้อ
    0.69
     アイアン
    0.69
    岸
    0.68
    粋
    0.68
    -//
    0.66
    科
    0.66
    ógica
    0.65
    ving
    0.64
    Act Density 0.000%

    No Known Activations