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

    Neuronpedia

    INDEX
    Explanations

    commands, finance, risk, date, development

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    颖
    0.40
     Первый
    0.40
    穎
    0.40
    ónicos
    0.38
     indexPath
    0.38
    oguć
    0.38
     nič
    0.37
    parser
    0.37
    PROTOCOL
    0.36
    liğini
    0.36
    POSITIVE LOGITS
     Armada
    0.38
     mulberry
    0.38
    츠
    0.36
    ふわ
    0.36
     트리플
    0.35
     Dusty
    0.35
     bottle
    0.34
     వర
    0.34
    geg
    0.33
    造成
    0.33
    Act Density 0.007%

    No Known Activations