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

    Neuronpedia

    INDEX
    Explanations

    title or heading

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    इंडियन
    0.52
    ennzeichnet
    0.48
    आपके
    0.46
     ಜನರ
    0.45
     испан
    0.45
     इंडियन
    0.44
     Aprend
    0.44
     Quân
    0.43
    TempVal
    0.43
     burada
    0.43
    POSITIVE LOGITS
    ↵
    0.49
     Title
    0.44
    -
    0.44
    Title
    0.43
    ;
    0.42
    ,
    0.41
    $:
    0.39
    \
    0.39
     prefer
    0.38
    :
    0.38
    Act Density 0.001%

    No Known Activations