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

    Neuronpedia

    INDEX
    Explanations

    image dimensions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    $response
    -0.07
    .^
    -0.06
     compliant
    -0.06
     Km
    -0.06
     /*!↵
    -0.06
    ({'
    -0.06
     заступ
    -0.06
    leads
    -0.06
    ẵ
    -0.06
    Chief
    -0.06
    POSITIVE LOGITS
     kích
    0.06
     ipad
    0.06
    金属
    0.06
     Dumbledore
    0.06
    мот
    0.06
    uchsia
    0.06
    								
↵
    0.06
    @@@@
    0.06
    _payment
    0.06
    Classifier
    0.06
    Act Density 0.011%

    No Known Activations