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

    Neuronpedia

    INDEX
    Explanations

    [[

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pregn
    -0.06
     gefunden
    -0.06
    (global
    -0.06
    Weights
    -0.06
    phans
    -0.06
     unofficial
    -0.06
     باش
    -0.06
    firstname
    -0.06
     ded
    -0.06
    snake
    -0.06
    POSITIVE LOGITS
    [channel
    0.07
    ustainability
    0.07
     Sustainability
    0.06
     /**↵
    0.06
    +++
    0.06
    腕
    0.06
     TimeInterval
    0.06
     REALLY
    0.06
    zel
    0.06
     anlay
    0.06
    Act Density 0.001%

    No Known Activations