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

    Neuronpedia

    INDEX
    Explanations

    starting with

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    5
    0.47
    馬上
    0.46
    ренные
    0.44
     resistor
    0.43
     albeit
    0.43
    ই
    0.43
    7
    0.43
    নের
    0.42
     incurring
    0.42
    гистра
    0.41
    POSITIVE LOGITS
     FROM
    0.53
     From
    0.48
     Ashanti
    0.47
     Ə
    0.46
    tig
    0.45
     dari
    0.44
    starting
    0.44
    从
    0.44
    จาก
    0.44
     từ
    0.43
    Act Density 0.049%

    No Known Activations