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

    Neuronpedia

    INDEX
    Explanations

    point

    np_max-act · gemini-2.0-flash

    keywords and constructs related to floating-point representation and behavior in programming languages.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    组织
    -0.06
    Concat
    -0.06
    Unmarshaller
    -0.06
     potential
    -0.06
     tor
    -0.06
     hid
    -0.06
    -commit
    -0.06
    reward
    -0.06
    اختی
    -0.06
     sed
    -0.06
    POSITIVE LOGITS
    fik
    0.06
    endants
    0.06
    �单
    0.06
    !",↵
    0.06
    :not
    0.06
     �
    0.06
     [=[
    0.06
    ALCHEMY
    0.06
     Adapter
    0.06
     refreshToken
    0.06
    Act Density 0.007%

    No Known Activations