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

    Neuronpedia

    INDEX
    Explanations

    JQuery selectors

    np_max-act · gemini-2.0-flash

    The neuron fires on numeric literals (especially decimal numbers) in code snippets.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     models
    -0.07
    raft
    -0.07
    Call
    -0.06
     якій
    -0.06
    illion
    -0.06
     Tanks
    -0.06
    ipl
    -0.06
    成為
    -0.06
     graduates
    -0.06
    iale
    -0.06
    POSITIVE LOGITS
     stark
    0.06
     createTime
    0.06
    getType
    0.06
     ath
    0.06
     yüksek
    0.06
     pra
    0.06
    StringValue
    0.06
    原因
    0.06
    LD
    0.06
     usted
    0.06
    Act Density 0.012%

    No Known Activations