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

    Neuronpedia

    INDEX
    Explanations

    section number or article number

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    르면
    0.39
    ຫານ
    0.34
     وإن
    0.34
     SOCKET
    0.34
    劻
    0.33
    ઞ
    0.33
     파일을
    0.32
    ຢ່າງ
    0.32
    <0x04>
    0.32
    级别
    0.32
    POSITIVE LOGITS
    0.38
    im
    0.36
    B
    0.33
    az
    0.31
     pre
    0.30
     dari
    0.30
    L
    0.30
     della
    0.30
    ter
    0.29
    casual
    0.29
    Act Density 0.003%

    No Known Activations