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

    Neuronpedia

    INDEX
    Explanations

    entry

    np_max-act · gemini-2.0-flash

    This neuron activates on phrases expressing per-unit rates or ratios (e.g. “entrada por cada …”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     ("<
    -0.07
     assist
    -0.06
     Summary
    -0.06
     seront
    -0.06
    ixed
    -0.06
     Airlines
    -0.06
    ebiliriz
    -0.06
     hair
    -0.06
    Pooling
    -0.06
     reducing
    -0.06
    POSITIVE LOGITS
     extravag
    0.06
    votes
    0.06
    entries
    0.06
    Rows
    0.06
     ดร
    0.06
    -ranging
    0.06
    ене
    0.06
     getClass
    0.06
     TableColumn
    0.06
    .CON
    0.06
    Act Density 0.028%

    No Known Activations