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

    Neuronpedia

    INDEX
    Explanations

    IDs and Code

    np_max-act · gemini-2.0-flash

    This neuron responds to fragments of hexadecimal identifiers (e.g. parts of UUIDs).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    _hidden
    -0.07
    thumbnails
    -0.07
    qi
    -0.06
    igua
    -0.06
    idae
    -0.06
     ALS
    -0.06
    igest
    -0.06
     CCT
    -0.06
    (send
    -0.06
    -legged
    -0.06
    POSITIVE LOGITS
     umbrella
    0.07
     отри
    0.07
     Publishers
    0.07
    ้อน
    0.06
    >'.↵
    0.06
     touchdowns
    0.06
     наблюд
    0.06
     Wishlist
    0.06
     '[
    0.06
     тому
    0.06
    Act Density 0.006%

    No Known Activations