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

    Neuronpedia

    INDEX
    Explanations

    Question answering

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    formatter
    -0.07
     preventing
    -0.06
    "])
↵
    -0.06
    ”↵
    -0.06
    _der
    -0.06
    (Graph
    -0.06
     tk
    -0.06
    &)↵
    -0.06
    msg
    -0.06
     counted
    -0.06
    POSITIVE LOGITS
    ॉट
    0.07
     RAND
    0.06
     Toyota
    0.06
    홈
    0.06
     unrest
    0.06
    ContentPane
    0.06
    ęp
    0.06
     नजर
    0.06
    getStatusCode
    0.06
     Львів
    0.06
    Act Density 0.122%

    No Known Activations