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

    Neuronpedia

    INDEX
    Explanations

    scientific texts

    np_max-act · gemini-2.0-flash

    The neuron detects terms describing the localization or distribution of molecules (e.g., proteins, mRNA) in scientific texts.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     canceled
    -0.07
     Recycling
    -0.06
     caught
    -0.06
    778
    -0.06
     buffering
    -0.06
     Engineering
    -0.06
     gracious
    -0.06
     sensor
    -0.06
     Pok
    -0.06
    676
    -0.06
    POSITIVE LOGITS
    CJK
    0.07
    ния
    0.06
    (!_
    0.06
     uží
    0.06
     검색
    0.06
     oid
    0.06
     accum
    0.06
    .Hit
    0.06
    .complete
    0.06
    iples
    0.06
    Act Density 0.020%

    No Known Activations