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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash

    the implementation details of transformer layers in PyTorch.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    א
    -0.07
    เอ
    -0.07
    害
    -0.07
    scheduler
    -0.07
     kul
    -0.06
     福
    -0.06
     Sydney
    -0.06
     killing
    -0.06
     LIC
    -0.06
    la
    -0.06
    POSITIVE LOGITS
    ManagedObject
    0.07
    crete
    0.06
    'email
    0.06
     eag
    0.06
    .setCurrent
    0.06
    (targets
    0.06
    ยนตร
    0.06
    ORIZED
    0.06
    .Failure
    0.06
    ableViewController
    0.06
    Act Density 0.405%

    No Known Activations