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

    Neuronpedia

    INDEX
    Explanations

    destruction

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     buoy
    -0.07
     tackles
    -0.07
    IFE
    -0.06
     annually
    -0.06
    -Javadoc
    -0.06
    /js
    -0.06
    華
    -0.06
    츠
    -0.06
     partisan
    -0.06
    房间
    -0.06
    POSITIVE LOGITS
    quiv
    0.07
    ınıza
    0.07
    idf
    0.06
    652
    0.06
    "label
    0.06
     $('[
    0.06
    ched
    0.06
    .em
    0.06
    (Cl
    0.06
    ].[
    0.06
    Act Density 0.034%

    No Known Activations