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

    Neuronpedia

    INDEX
    Explanations

    questions and answers

    np_max-act · gemini-2.0-flash

    This neuron is primarily detecting the model’s internal metadata markers (e.g. the special <|start_header_id|> token).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     freeze
    -0.07
     RID
    -0.07
     حی
    -0.06
    Mission
    -0.06
    806
    -0.06
     заказ
    -0.06
    activ
    -0.06
     operands
    -0.06
    宣
    -0.06
     rollout
    -0.06
    POSITIVE LOGITS
    .TryGetValue
    0.07
    ück
    0.07
    OMPI
    0.07
    PLY
    0.07
    proxy
    0.07
     Miller
    0.06
    uuml
    0.06
     spiked
    0.06
    ordinate
    0.06
    илися
    0.06
    Act Density 0.005%

    No Known Activations