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

    Neuronpedia

    INDEX
    Explanations

    pone

    np_max-act · gemini-2.0-flash

    This neuron detects in‐text citation markers (in particular the “pone” tokens within reference tags).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     LF
    -0.07
    .monitor
    -0.07
    .Values
    -0.07
    範
    -0.06
    iêm
    -0.06
    _CI
    -0.06
    _rs
    -0.06
    shows
    -0.06
    (ar
    -0.06
    قف
    -0.06
    POSITIVE LOGITS
     Rename
    0.07
     stata
    0.06
    -filled
    0.06
     ongoing
    0.06
     valleys
    0.06
     lives
    0.06
     والتي
    0.06
     writeTo
    0.06
     sme
    0.06
     hashes
    0.06
    Act Density 0.002%

    No Known Activations