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

    Neuronpedia

    INDEX
    Explanations

    code/data snippets

    np_max-act · gemini-2.0-flash

    The neuron specifically fires on the “C” key in the little JSON‐style response object—that is, it detects the classifier’s “C” label token in the output dictionary.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     eth
    -0.07
     powdered
    -0.06
    リーズ
    -0.06
    Planning
    -0.06
    _LED
    -0.06
    _TERM
    -0.06
    _pes
    -0.06
     Країна
    -0.06
    ondrous
    -0.06
    PRESSION
    -0.06
    POSITIVE LOGITS
     ru
    0.06
     prejudices
    0.06
    HeaderView
    0.06
    -tax
    0.06
     compens
    0.06
     Spears
    0.06
     cartoons
    0.06
    eldon
    0.06
     nothing
    0.06
     Marlins
    0.06
    Act Density 0.004%

    No Known Activations