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

    Neuronpedia

    INDEX
    Explanations

    explaining a situation or solution

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Fridge
    0.46
     AML
    0.45
    !"
    0.44
     Header
    0.43
     Consumer
    0.43
    ati
    0.42
    ₺
    0.42
    ٦
    0.42
     Amer
    0.41
     Distribution
    0.41
    POSITIVE LOGITS
    کول
    0.51
    shortcuts
    0.45
    inputenc
    0.45
    юнча
    0.44
     querida
    0.44
    helby
    0.44
    انت
    0.44
    コート
    0.44
    الان
    0.43
     Lobkovic
    0.43
    Act Density 0.002%

    No Known Activations