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

    Neuronpedia

    INDEX
    Explanations

    Barcelona attractions

    np_max-act · gemini-2.0-flash

    This neuron detects mentions of specific place or landmark names (proper nouns for attractions).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    PlainText
    -0.06
     standout
    -0.06
     سیاسی
    -0.06
    (full
    -0.06
    _Con
    -0.06
    ERIC
    -0.06
    (line
    -0.06
    _Rem
    -0.06
     voting
    -0.06
    emperature
    -0.06
    POSITIVE LOGITS
    ouve
    0.07
    ентом
    0.06
    terraform
    0.06
     rogue
    0.06
    .Edit
    0.06
     بحث
    0.06
     Recover
    0.06
    relu
    0.06
    abinet
    0.06
     subsidy
    0.06
    Act Density 0.004%

    No Known Activations