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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Separ
    -0.06
    TURE
    -0.06
    /c
    -0.06
    �
    -0.06
     coun
    -0.06
    ีเอ
    -0.06
     Т
    -0.06
    GRESS
    -0.06
    един
    -0.06
    วาม
    -0.06
    POSITIVE LOGITS
     dışı
    0.07
     $\
    0.07
    "?↵↵
    0.06
     dong
    0.06
     ONLINE
    0.06
    (byte
    0.06
     Stunden
    0.06
     Não
    0.06
    wang
    0.06
    /testing
    0.06
    Act Density 0.197%

    No Known Activations