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

    Neuronpedia

    INDEX
    Explanations

    temporal

    np_max-act · gemini-2.0-flash

    The neuron detects mentions of spatial and temporal descriptors, i.e. “spatiotemporal” contexts in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     luôn
    -0.07
     richtig
    -0.07
    alah
    -0.06
     Bowie
    -0.06
    ."]
    -0.06
     celebrated
    -0.06
    -->↵
    -0.06
     July
    -0.06
     Dra
    -0.06
     Brandon
    -0.06
    POSITIVE LOGITS
    terms
    0.08
    たし
    0.07
    DATA
    0.07
     extingu
    0.07
     tail
    0.07
    irection
    0.07
     lex
    0.06
    Vectorizer
    0.06
     ERP
    0.06
    umat
    0.06
    Act Density 0.006%

    No Known Activations