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

    Neuronpedia

    INDEX
    Explanations

    embedding

    np_max-act · gemini-2.0-flash

    coding-related discussions and instructions.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    496
    -0.07
     dopamine
    -0.07
     rat
    -0.07
     mại
    -0.07
     ${
    -0.07
    _frac
    -0.07
     Taylor
    -0.07
     Jian
    -0.07
    _type
    -0.06
     Sai
    -0.06
    POSITIVE LOGITS
     emb
    0.10
     Emb
    0.10
    Emb
    0.09
     embark
    0.08
    mmo
    0.08
     Embassy
    0.08
    بار
    0.08
    mma
    0.08
     embarked
    0.08
     έως
    0.07
    Act Density 0.018%

    No Known Activations