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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     بغ
    -0.07
    为
    -0.06
    580
    -0.06
     nghiệ
    -0.06
     adul
    -0.06
    mdi
    -0.06
    atha
    -0.06
    -launch
    -0.06
     siyasi
    -0.06
     önem
    -0.06
    POSITIVE LOGITS
    stores
    0.06
    ancial
    0.06
    ций
    0.06
     visceral
    0.06
    _layers
    0.06
    �
    0.06
     Cancer
    0.06
    =models
    0.06
    _java
    0.06
    .Servlet
    0.06
    Act Density 0.093%

    No Known Activations