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

    Neuronpedia

    INDEX
    Explanations

    Names

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    "])
↵
    -0.07
     antig
    -0.06
    	effect
    -0.06
     CLASS
    -0.06
    District
    -0.06
    續
    -0.06
     kcal
    -0.06
    Mat
    -0.06
     datos
    -0.06
    _RG
    -0.06
    POSITIVE LOGITS
    開発
    0.07
    ashion
    0.07
    _WIFI
    0.07
    (worker
    0.06
    endencies
    0.06
     evidently
    0.06
     Hawaii
    0.06
    -yyyy
    0.06
    시키
    0.06
    IMIT
    0.06
    Act Density 0.027%

    No Known Activations