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

    Neuronpedia

    INDEX
    Explanations

    quotation marks

    np_max-act · gemini-2.0-flash

    This neuron detects track‐listing time stamps (minute:second durations).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    cwd
    -0.07
    -org
    -0.06
    CACHE
    -0.06
    (pk
    -0.06
    datal
    -0.06
     ‏
    -0.06
    _S
    -0.06
    *(
    -0.06
     tk
    -0.06
     交
    -0.06
    POSITIVE LOGITS
    eming
    0.06
     mạng
    0.06
     �
    0.06
    mint
    0.06
     форм
    0.06
     accordingly
    0.06
     Evalu
    0.06
     cinsel
    0.06
    .protocol
    0.06
    로운
    0.06
    Act Density 0.007%

    No Known Activations