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

    Neuronpedia

    INDEX
    Explanations

    Includes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     direction
    -0.07
    scene
    -0.07
    。”
    -0.07
    StackTrace
    -0.06
    ικές
    -0.06
    ’t
    -0.06
     punishments
    -0.06
    ема
    -0.06
     könnte
    -0.06
    .dictionary
    -0.06
    POSITIVE LOGITS
    
    0.07
    bron
    0.07
     @{$
    0.06
     أمريكي
    0.06
    xCE
    0.06
    layan
    0.06
    lijah
    0.06
     difer
    0.06
     Daytona
    0.06
     кал
    0.06
    Act Density 0.032%

    No Known Activations