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

    Neuronpedia

    INDEX
    Explanations

    This is

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    где
    0.45
    нде
    0.45
    where
    0.41
     where
    0.38
    metric
    0.38
     hvor
    0.38
     cityName
    0.37
    ুব্ধ
    0.37
     hapl
    0.37
    Glam
    0.37
    POSITIVE LOGITS
     echt
    0.56
     continuation
    0.53
     vraiment
    0.50
     정말
    0.49
     davvero
    0.48
     मेरा
    0.46
     disgusting
    0.45
     ridiculous
    0.45
    Really
    0.45
    真是
    0.45
    Act Density 0.000%

    No Known Activations