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

    Neuronpedia

    INDEX
    Explanations

    squares

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _dims
    -0.07
    }}"↵
    -0.06
     numbering
    -0.06
     ケ
    -0.06
     boundary
    -0.06
    olut
    -0.06
    .Graph
    -0.06
     Buddha
    -0.06
     VM
    -0.06
     resto
    -0.06
    POSITIVE LOGITS
     squared
    0.07
     obtaining
    0.07
    飞
    0.06
    vik
    0.06
    MouseEvent
    0.06
     Ting
    0.06
     Estr
    0.06
    tabs
    0.06
     inscription
    0.06
    DidChange
    0.06
    Act Density 0.011%

    No Known Activations