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

    Neuronpedia

    INDEX
    Explanations

    TripAdvisor reviews

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ,c
    -0.07
     と
    -0.07
    。。
    -0.06
     STATUS
    -0.06
    来了
    -0.06
    	as
    -0.06
    cstdlib
    -0.06
    /address
    -0.06
    ),$
    -0.06
    ^K
    -0.06
    POSITIVE LOGITS
    Sugar
    0.07
    izzling
    0.07
     Muj
    0.06
    .addAction
    0.06
     Deadly
    0.06
    rites
    0.06
     homicides
    0.06
    -haired
    0.06
    windows
    0.06
    486
    0.06
    Act Density 0.004%

    No Known Activations