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

    Neuronpedia

    INDEX
    Explanations

    143

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     kır
    -0.06
    ;


↵
    -0.05
     republiky
    -0.05
     इसम
    -0.05
    polygon
    -0.05
    interest
    -0.05
     Airbnb
    -0.05
     aime
    -0.05
    -bootstrap
    -0.05
    mort
    -0.05
    POSITIVE LOGITS
    (rc
    0.07
    �
    0.07
     Kaplan
    0.07
    WithIdentifier
    0.07
    ρευ
    0.07
    δη
    0.07
    .Wrap
    0.07
    �
    0.07
    /controller
    0.07
    фик
    0.07
    Act Density 13.935%

    No Known Activations