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

    Neuronpedia

    INDEX
    Explanations

    Thinking/calculation

    np_max-act · gemini-2.0-flash

    The neuron detects “chain‐of‐thought” prompt language—phrases like “think … step by step.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    .faceVertexUvs
    -0.07
    icts
    -0.07
    -turn
    -0.07
    规范
    -0.07
    Playlist
    -0.06
     распрост
    -0.06
     enn
    -0.06
    ி
    -0.06
    层
    -0.06
    进一步
    -0.06
    POSITIVE LOGITS
     Hang
    0.06
     Sexual
    0.06
     eb
    0.06
     relação
    0.06
    (dynamic
    0.06
     yolc
    0.06
     Sergio
    0.06
    　　　　　
    0.06
    ンス
    0.06
     Pot
    0.06
    Act Density 0.002%

    No Known Activations