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

    Neuronpedia

    INDEX
    Explanations

    with

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Static
    -0.07
    -zero
    -0.07
    <Field
    -0.07
    /news
    -0.06
     restored
    -0.06
     价格
    -0.06
    订单
    -0.06
     چه
    -0.06
     soğuk
    -0.06
    Nevertheless
    -0.06
    POSITIVE LOGITS
     marketing
    0.07
    _shell
    0.06
     ether
    0.06
     br
    0.06
     ec
    0.06
    aten
    0.06
    こんにちは
    0.06
    vní
    0.06
    goo
    0.06
     luận
    0.06
    Act Density 0.005%

    No Known Activations