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

    Neuronpedia

    INDEX
    Explanations

    Uncertainty of future

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     kettle
    -0.09
    ī
    -0.08
     Emperor
    -0.07
    "B
    -0.07
     EF
    -0.07
     -->
↵
    -0.07
     dry
    -0.07
     Swagger
    -0.07
    רוח
    -0.07
     moet
    -0.07
    POSITIVE LOGITS
     budding
    0.07
     pii
    0.07
    )did
    0.07
     dipl
    0.07
    分校
    0.07
    Led
    0.07
    ++){
    0.07
    𝖇
    0.07
    走过
    0.07
     ThreadPool
    0.07
    Act Density 0.122%

    No Known Activations