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

    Neuronpedia

    INDEX
    Explanations

    code separators and keywords

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     факторов
    0.54
    вной
    0.51
    剰
    0.51
    議
    0.49
     gigs
    0.48
     bzw
    0.47
    墓
    0.47
     depreci
    0.46
    wbr
    0.45
     tienden
    0.45
    POSITIVE LOGITS
    asını
    0.56
    úrese
    0.56
    URDAY
    0.55
     seconda
    0.52
     Në
    0.52
     Ông
    0.51
     În
    0.51
    UNDE
    0.51
     İ
    0.50
     ዋና
    0.50
    Act Density 0.031%

    No Known Activations