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

    Neuronpedia

    INDEX
    Explanations

    say "Server"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    lıklı
    -0.07
     铁
    -0.07
    crew
    -0.07
    _NE
    -0.07
    EK
    -0.06
     CI
    -0.06
     parsing
    -0.06
     brewery
    -0.06
     fraught
    -0.06
     curing
    -0.06
    POSITIVE LOGITS
    žití
    0.07
     využití
    0.06
     أنها
    0.06
    änd
    0.06
    _EMPTY
    0.06
     projev
    0.06
    šší
    0.06
     spolup
    0.06
    )();↵
    0.06
     århus
    0.06
    Act Density 0.004%

    No Known Activations