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

    Neuronpedia

    INDEX
    Explanations

    chat

    np_max-act · gemini-2.0-flash

    The neuron fires on occurrences of the word “chat” (i.e. chat/channel metadata).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ail
    -0.07
    pio
    -0.07
    uples
    -0.06
    earch
    -0.06
    ателя
    -0.06
    lsruhe
    -0.06
    TAIL
    -0.06
    .fromJson
    -0.06
    $app
    -0.06
    nama
    -0.06
    POSITIVE LOGITS
     tricks
    0.06
     	↵
    0.06
     cra
    0.06
     unlikely
    0.06
    :list
    0.06
      ↵
    0.06
    <HTMLInputElement
    0.06
    AILY
    0.06
    <My
    0.06
    >You
    0.06
    Act Density 0.006%

    No Known Activations