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

    Neuronpedia

    INDEX
    Explanations

    000

    np_max-act · gemini-2.0-flash

    The neuron activates on the “000” tokens in the timestamp/timezone offset fields (e.g. “+000”) in metadata headers.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    France
    -0.07
     departamento
    -0.06
     initiative
    -0.06
    یره
    -0.06
     Destination
    -0.06
    xffffffff
    -0.06
    İn
    -0.06
    ơm
    -0.06
     crisis
    -0.06
     Accum
    -0.06
    POSITIVE LOGITS
     bern
    0.08
    mania
    0.06
     Rails
    0.06
    　　
    0.06
    permissions
    0.06
     gro
    0.06
    (meta
    0.06
    .removeItem
    0.06
    	content
    0.06
     pissed
    0.06
    Act Density 0.001%

    No Known Activations