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

    Neuronpedia

    INDEX
    Explanations

    established by, deeply happy, already taxed

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     موږ
    0.80
    Co
    0.77
    asidd
    0.75
     süreç
    0.75
    Jika
    0.74
     landslides
    0.74
    Sumber
    0.73
    Untuk
    0.73
    Convers
    0.73
    Enfin
    0.73
    POSITIVE LOGITS
    iak
    0.72
    𝐦
    0.72
     gave
    0.70
    습니다
    0.70
    зив
    0.70
     đeo
    0.69
    рин
    0.68
    𝐬
    0.68
     справи
    0.67
     someone
    0.66
    Act Density 0.000%

    No Known Activations