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

    Neuronpedia

    INDEX
    Explanations

    eclipses and Earth/Sun/Moon positions

    np_max-act · gemini-2.0-flash

    This neuron detects the special header‐boundary tokens (e.g. `<|start_header_id|>` and `<|end_header_id|>`) in the text stream.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     mari
    -0.07
    handlers
    -0.07
     مهندسی
    -0.06
     fleeting
    -0.06
     Evaluate
    -0.06
     bottom
    -0.06
     fieldName
    -0.06
    .Manifest
    -0.06
     обл
    -0.06
    -offset
    -0.06
    POSITIVE LOGITS
     Url
    0.07
    ritten
    0.06
    rostřed
    0.06
    ("---
    0.06
    piel
    0.06
    ổ
    0.06
    ...");↵
    0.06
    (yy
    0.06
    ẩm
    0.06
    нося
    0.06
    Act Density 0.008%

    No Known Activations