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

    Neuronpedia

    INDEX
    Explanations

    ag or Ag followed by a word

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ையான
    0.37
    থন
    0.37
    ثمان
    0.36
    Ꮠ
    0.36
     ܕ
    0.35
    鐩
    0.35
    㐸
    0.35
    EmbeddedResource
    0.34
    ровано
    0.34
    寰
    0.34
    POSITIVE LOGITS
    Ag
    2.86
     Ag
    2.69
     ag
    2.45
     AG
    2.42
    ag
    2.39
    AG
    2.34
     Agnes
    2.19
     agg
    2.11
     Agg
    2.09
     Agatha
    1.98
    Act Density 0.079%

    No Known Activations