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

    Neuronpedia

    INDEX
    Explanations

    using namespace

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ي
    0.75
    )
    0.73
    on
    0.70
    دخل
    0.67
    ]
    0.67
    י
    0.65
     regarde
    0.63
     dispens
    0.62
     reincarn
    0.61
    د
    0.61
    POSITIVE LOGITS
    <0x91>
    0.61
     in
    0.55
     Наши
    0.55
     თ
    0.54
    <0x83>
    0.53
     Gesch
    0.52
    <0x98>
    0.52
     Dukes
    0.50
     พิ
    0.49
     Valley
    0.49
    Act Density 0.001%

    No Known Activations