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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     शक
    -0.07
    )];↵↵
    -0.06
    PHY
    -0.06
    ît
    -0.06
    ากาศ
    -0.06
    ĞI
    -0.06
     localized
    -0.06
    !"↵
    -0.06
    ".
    -0.06
     nakonec
    -0.05
    POSITIVE LOGITS
     reckon
    0.07
    reserved
    0.07
     unrest
    0.07
     Port
    0.07
     нож
    0.07
    await
    0.07
    -request
    0.07
     port
    0.07
     Ducks
    0.07
    -env
    0.06
    Act Density 0.076%

    No Known Activations