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

    Neuronpedia

    INDEX
    Explanations

    Code and XML-related texts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     painted
    -0.08
    ();↵↵
    -0.07
     �
    -0.07
    >No
    -0.07
     drought
    -0.07
    ();↵
    -0.07
    >()
    -0.06
     Viewer
    -0.06
    <>();
↵
    -0.06
    `.↵
    -0.06
    POSITIVE LOGITS
     Vậy
    0.07
     э
    0.07
     alex
    0.06
    NavigationBar
    0.06
     beyaz
    0.06
     електрон
    0.06
     基
    0.06
    ]‏
    0.06
    automatic
    0.06
     Раз
    0.06
    Act Density 0.015%

    No Known Activations