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

    Neuronpedia

    INDEX
    Explanations

    Arts and cultural events

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     дых
    -0.06
     Royals
    -0.06
     возраст
    -0.06
    考
    -0.06
     Provincial
    -0.06
     آپ
    -0.06
     خدم
    -0.06
     Disco
    -0.06
     싱글
    -0.06
     тоб
    -0.06
    POSITIVE LOGITS
     tri
    0.07
     Indeed
    0.06
    ٥
    0.06
    ircular
    0.06
    設備
    0.06
     softmax
    0.06
    orelease
    0.06
     referring
    0.06
    ีเอ
    0.06
    าจาก
    0.06
    Act Density 0.051%

    No Known Activations