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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ```↵
    -0.08
    _left
    -0.08
    -inc
    -0.07
    iv
    -0.07
     freeing
    -0.07
    ↵            
↵
    -0.07
     ted
    -0.07
    их
    -0.06
     bankers
    -0.06
     ing
    -0.06
    POSITIVE LOGITS
    .simple
    0.07
     Typography
    0.06
     renderItem
    0.06
    Twig
    0.06
    장
    0.06
    “All
    0.06
    .getAll
    0.06
    urlpatterns
    0.05
     Ack
    0.05
     FINAL
    0.05
    Act Density 0.205%

    No Known Activations