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

    Neuronpedia

    INDEX
    Explanations

    locations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .mime
    -0.08
     Cone
    -0.07
    -0.07
    Lee
    -0.06
    公園
    -0.06
     Criteria
    -0.06
    40
    -0.06
    16
    -0.06
    -0.06
    商
    -0.06
    POSITIVE LOGITS
    Putin
    0.07
    (PDO
    0.07
    �
    0.06
     незалеж
    0.06
    сько
    0.06
     predecessor
    0.06
     قد
    0.06
     Constantin
    0.06
     dostate
    0.06
     ayrı
    0.06
    Act Density 0.122%

    No Known Activations