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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Woods
    -0.07
    urry
    -0.06
    _width
    -0.06
     inj
    -0.06
    Above
    -0.06
     eval
    -0.06
    ysl
    -0.06
     //(
    -0.06
    .Short
    -0.06
    gist
    -0.06
    POSITIVE LOGITS
     *__
    0.06
    piar
    0.06
     мира
    0.06
    ?=.*
    0.06
    =$("#
    0.06
     skb
    0.06
     město
    0.06
     ventas
    0.06
    0.06
    “This
    0.06
    Act Density 0.053%

    No Known Activations