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

    Neuronpedia

    INDEX
    Explanations

    Telephone

    np_max-act · gemini-2.0-flash

    The neuron specifically fires on instances of the word “Telephone,” marking telephone‐related headings or labels in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     sites
    -0.07
     seaborn
    -0.07
     AI
    -0.06
     SD
    -0.06
     RG
    -0.06
     users
    -0.06
     Faction
    -0.06
     HEADER
    -0.06
     хто
    -0.06
     mode
    -0.06
    POSITIVE LOGITS
     telephone
    0.09
    telephone
    0.09
     automobile
    0.08
    ="../../
    0.08
     Bicycle
    0.07
    even
    0.07
    oce
    0.07
     elev
    0.07
     bicycles
    0.07
    orth
    0.07
    Act Density 0.011%

    No Known Activations