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

    Neuronpedia

    INDEX
    Explanations

    research

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     preview
    -0.07
     meal
    -0.07
     Garden
    -0.07
     tree
    -0.07
     shortcuts
    -0.06
    γκε
    -0.06
     tire
    -0.06
    ène
    -0.06
     کاری
    -0.06
     danske
    -0.06
    POSITIVE LOGITS
    الأ
    0.07
    []{"
    0.06
     Nel
    0.06
    "><?
    0.06
    ritz
    0.06
     milion
    0.06
    postData
    0.06
    camel
    0.06
     ジ
    0.06
     neste
    0.06
    Act Density 0.107%

    No Known Activations