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

    Neuronpedia

    INDEX
    Explanations

    colon

    np_max-act · gemini-2.0-flash

    This neuron spotlights the “A:” answer label at the start of answer blocks.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     ELECT
    -0.06
    roupon
    -0.06
     Computes
    -0.06
    .fast
    -0.06
     alliances
    -0.06
    instruction
    -0.06
    	mp
    -0.06
     Thổ
    -0.06
     chiefly
    -0.06
    �
    -0.06
    POSITIVE LOGITS
    esting
    0.07
    20
    0.07
    명을
    0.06
     colourful
    0.06
     máme
    0.06
    ентов
    0.06
     Drag
    0.06
    ItemAt
    0.06
     Decom
    0.06
    戴
    0.06
    Act Density 0.034%

    No Known Activations