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

    Neuronpedia

    INDEX
    Explanations

    commas

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    leg
    -0.07
    pulse
    -0.07
    LEG
    -0.07
     iam
    -0.06
    CLS
    -0.06
     disposal
    -0.06
     \|
    -0.06
     LogLevel
    -0.06
    MF
    -0.06
    为
    -0.06
    POSITIVE LOGITS
     scé
    0.06
     पश
    0.06
    IMITER
    0.06
    (Schedulers
    0.06
     ThreadPool
    0.06
     PVOID
    0.06
    uestas
    0.06
    �
    0.06
    ุนายน
    0.06
    標
    0.06
    Act Density 0.287%

    No Known Activations