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

    Neuronpedia

    INDEX
    Explanations

    quotation mark

    np_max-act · gemini-2.0-flash

    The neuron fires on JSON‐style object property names—that is, the quoted keys in a metadata record.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     longest
    -0.07
     đúng
    -0.07
     windshield
    -0.06
     hd
    -0.06
    <Action
    -0.06
    .ReadAllText
    -0.06
    ution
    -0.06
     wraps
    -0.06
    Ctx
    -0.06
    .hstack
    -0.06
    POSITIVE LOGITS
    /de
    0.07
     ");
↵
    0.06
    fact
    0.06
    -find
    0.06
    	Expect
    0.06
    ีส
    0.06
     spree
    0.06
     turn
    0.06
     zih
    0.06
    _MED
    0.06
    Act Density 0.004%

    No Known Activations