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

    Neuronpedia

    INDEX
    Explanations

    foreign words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    udge
    -0.07
    ajo
    -0.07
     constitute
    -0.07
     delle
    -0.07
     nelle
    -0.07
    싼
    -0.07
     Strike
    -0.07
    .React
    -0.07
    iore
    -0.07
     trochę
    -0.07
    POSITIVE LOGITS
    主人
    0.07
     televised
    0.06
    ソフト
    0.06
    キャンペ
    0.06
     Opera
    0.06
    ComputedStyle
    0.06
     gönder
    0.06
    郵
    0.06
     prophets
    0.06
    让她
    0.06
    Act Density 0.169%

    No Known Activations