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

    Neuronpedia

    INDEX
    Explanations

    raised

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     verses
    -0.07
     punching
    -0.07
    <input
    -0.07
     youthful
    -0.07
     winding
    -0.06
     yang
    -0.06
     Baker
    -0.06
     Copa
    -0.06
    ";↵↵
    -0.06
    Hang
    -0.06
    POSITIVE LOGITS
     xpath
    0.07
     відсут
    0.06
     семей
    0.06
     Xamarin
    0.06
    置
    0.06
     Tibetan
    0.06
     hasNext
    0.06
    \uD
    0.06
     �
    0.06
    孝
    0.06
    Act Density 0.010%

    No Known Activations