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

    Neuronpedia

    INDEX
    Explanations

    HDD replaced with

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     acompan
    0.81
    掑
    0.72
     عبر
    0.70
     junto
    0.67
     فائدہ
    0.67
     lâu
    0.65
    ผ่าน
    0.65
     കൂടി
    0.64
     využ
    0.64
     ausgestattet
    0.64
    POSITIVE LOGITS
     with
    2.42
    with
    2.27
    With
    2.19
     dengan
    2.05
    ด้วย
    1.99
     With
    1.98
     avec
    1.98
     với
    1.98
    Dengan
    1.81
    dengan
    1.76
    Act Density 0.430%

    No Known Activations