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

    Neuronpedia

    INDEX
    Explanations

    question and explanation markers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Harga
    0.98
     Pandas
    0.91
     Preise
    0.90
     finition
    0.89
     しかし
    0.88
     Prices
    0.88
     関数
    0.87
     ราคา
    0.86
    Harga
    0.86
     Genel
    0.85
    POSITIVE LOGITS
     under
    0.82
    wall
    0.81
     shaving
    0.81
     wall
    0.80
    under
    0.77
    ویت
    0.76
    vitamin
    0.75
    Under
    0.72
    non
    0.70
    neut
    0.70
    Act Density 0.000%

    No Known Activations