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

    Neuronpedia

    INDEX
    Explanations

    code licenses

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Disposable
    -0.07
    .pref
    -0.06
    、ア
    -0.06
    uji
    -0.06
    /day
    -0.06
    خراج
    -0.06
     者
    -0.06
    international
    -0.05
     extension
    -0.05
    هور
    -0.05
    POSITIVE LOGITS
    土
    0.07
    gunta
    0.07
     Soap
    0.07
     covers
    0.07
    ны
    0.07
    单
    0.07
    迷
    0.06
     سریال
    0.06
    -quote
    0.06
     Baths
    0.06
    Act Density 0.001%

    No Known Activations