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

    Neuronpedia

    INDEX
    Explanations

    questions and prompts

    np_max-act · gemini-2.0-flash

    This neuron activates on list‐style “What are … that …” questions—i.e. interrogative requests like “What are popular/leading/important X that …?”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    metrics related to the evaluation of generative question-answering tasks.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    olume
    -0.07
    subtract
    -0.07
    filer
    -0.07
    cloth
    -0.06
    six
    -0.06
     %#
    -0.06
    izando
    -0.06
    岁
    -0.06
    ساب
    -0.06
    fov
    -0.06
    POSITIVE LOGITS
    _DESTROY
    0.06
    /modules
    0.06
     (%)
    0.06
    [root
    0.06
    elseif
    0.06
    .REG
    0.06
    DateFormat
    0.06
    [mid
    0.06
     postupně
    0.06
     Woj
    0.06
    Act Density 0.114%

    No Known Activations