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

    Neuronpedia

    INDEX
    Explanations

    S

    np_max-act · gemini-2.0-flash

    This neuron detects uppercase media‐agency or source acronyms (e.g. “IANS,” “ANS,” “CNN,” etc.) that tag article bylines or photo credits.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    製
    -0.07
     Merr
    -0.07
     nop
    -0.07
     Doyle
    -0.06
     Fur
    -0.06
    वर
    -0.06
     Jazz
    -0.06
     عشر
    -0.06
    zip
    -0.06
     gentlemen
    -0.06
    POSITIVE LOGITS
     onc
    0.06
    感じ
    0.06
    .preview
    0.06
    グル
    0.06
     arcade
    0.06
     pathways
    0.06
     safely
    0.06
    ampilkan
    0.06
     zaměstnan
    0.06
    ться
    0.06
    Act Density 0.030%

    No Known Activations