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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ---------------------------------------------------------------------------↵
    -0.07
     Bakanı
    -0.07
     demonstrate
    -0.07
    ◅
    -0.07
     góp
    -0.07
    )'),↵
    -0.06
    大切な
    -0.06
     appropri
    -0.06
    ্
    -0.06
    单职业
    -0.06
    POSITIVE LOGITS
     Camera
    0.07
    azing
    0.07
    _arrow
    0.07
     baz
    0.07
     Fall
    0.07
    WebView
    0.07
    य
    0.07
    ssql
    0.07
    찻
    0.07
    tons
    0.07
    Act Density 0.002%

    No Known Activations