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

    Neuronpedia

    INDEX
    Explanations

    code or technical text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     berth
    -0.07
    学院
    -0.06
     WARRANTIES
    -0.06
    _topics
    -0.06
     getService
    -0.06
     '(
    -0.06
    _OPTIONS
    -0.06
    Thin
    -0.06
    *)_
    -0.06
    .ctx
    -0.06
    POSITIVE LOGITS
     aldığı
    0.07
     sarcast
    0.07
     анти
    0.07
    bart
    0.07
     ava
    0.06
    emodel
    0.06
    γού
    0.06
    oxide
    0.06
     Ronald
    0.06
    ific
    0.06
    Act Density 0.078%

    No Known Activations