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

    Neuronpedia

    INDEX
    Explanations

    recommendations or assurances

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    кас
    -0.06
    lc
    -0.06
     trapped
    -0.06
     circular
    -0.06
    ห
    -0.06
    redict
    -0.06
    	let
    -0.06
     junior
    -0.06
     왔
    -0.06
    Dynamic
    -0.06
    POSITIVE LOGITS
     conditional
    0.07
    альну
    0.07
    utto
    0.06
    nda
    0.06
     Brasil
    0.06
    .getLabel
    0.06
    ?)↵↵
    0.06
     Kraj
    0.06
     فيها
    0.06
    ?↵↵↵
    0.06
    Act Density 0.091%

    No Known Activations