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

    Neuronpedia

    INDEX
    Explanations

    Lake names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     অবি
    0.71
    无
    0.67
    દાર
    0.67
    hz
    0.67
    ंका
    0.66
    無
    0.65
     კომ
    0.65
    赫
    0.64
    prayer
    0.64
    pc
    0.64
    POSITIVE LOGITS
     Victoria
    1.06
    Victoria
    0.94
     victoria
    0.94
     Albert
    0.86
     VICTOR
    0.86
     notebooks
    0.85
     Альбер
    0.82
    वैज्ञानिक
    0.81
     Victorian
    0.79
    albumin
    0.77
    Act Density 0.003%

    No Known Activations