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

    Neuronpedia

    INDEX
    Explanations

    specific words followed by punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     eet
    0.77
    {
    0.71
    凝
    0.71
    **
    0.70
    size
    0.68
    st
    0.67
     private
    0.64
     ep
    0.64
    ***
    0.64
     שת
    0.64
    POSITIVE LOGITS
     INSPIRE
    0.84
    ੭
    0.78
    あなたが
    0.76
    座標
    0.75
    ⵍ
    0.74
     BLUENRG
    0.73
    ंबकीय
    0.73
    ร
    0.73
     elettronica
    0.73
    ্ল
    0.71
    Act Density 0.013%

    No Known Activations