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

    Neuronpedia

    INDEX
    Explanations

    academic metrics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    வல்
    0.49
     yılı
    0.49
    alek
    0.46
    alid
    0.45
    Interceptor
    0.45
    qat
    0.44
     Sood
    0.44
    𝑫
    0.44
    setUser
    0.43
     прогу
    0.43
    POSITIVE LOGITS
    '
    0.51
     atraer
    0.48
    "
    0.46
    ف
    0.44
     como
    0.44
     Frankie
    0.44
     HIV
    0.42
     LGBT
    0.41
     potreb
    0.41
    やや
    0.41
    Act Density 0.002%

    No Known Activations