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

    Neuronpedia

    INDEX
    Explanations

    languages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    zenia
    -0.08
     vitamina
    -0.08
    字号
    -0.07
    ứng
    -0.07
     பட
    -0.07
     Fixed
    -0.07
     занима
    -0.07
    589
    -0.07
     processamento
    -0.07
    zyc
    -0.07
    POSITIVE LOGITS
    favorite
    0.08
     affection
    0.08
    Favorite
    0.08
     différentes
    0.08
     approximately
    0.08
    ทั้งหมด
    0.07
    'époque
    0.07
    .messaging
    0.07
     taum
    0.07
     puse
    0.07
    Act Density 0.014%

    No Known Activations