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

    Neuronpedia

    INDEX
    Explanations

    ide

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     khởi
    -0.07
    、大
    -0.07
     Stern
    -0.07
     followers
    -0.06
     Forest
    -0.06
    /work
    -0.06
     gm
    -0.06
     pea
    -0.06
     frost
    -0.06
     caps
    -0.06
    POSITIVE LOGITS
    ัจจ
    0.07
    &oacute
    0.07
     FileName
    0.06
     LogManager
    0.06
    ");}↵
    0.06
    ứa
    0.06
     계
    0.06
    Middleware
    0.06
    ROWS
    0.06
     datastore
    0.06
    Act Density 0.002%

    No Known Activations