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

    Neuronpedia

    INDEX
    Explanations

    HEADER

    np_max-act · gemini-2.0-flash

    Explanation of neuron 4 behavior: the main thing this neuron does is find the token “HEADER,” particularly in file‐header comment blocks.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    prt
    -0.07
     ingredient
    -0.07
     seminal
    -0.07
     Mara
    -0.07
     Marin
    -0.06
     Capability
    -0.06
    adding
    -0.06
    _Detail
    -0.06
    Compact
    -0.06
     Dominic
    -0.06
    POSITIVE LOGITS
     createdAt
    0.06
     carbohydr
    0.06
     percent
    0.06
    (skb
    0.06
    Configurer
    0.06
    .gridx
    0.06
    ritable
    0.06
    那种
    0.06
     offers
    0.06
     Coca
    0.06
    Act Density 0.000%

    No Known Activations