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

    Neuronpedia

    INDEX
    Explanations

    instructions and descriptions

    np_max-act · gemini-2.0-flash

    The neuron flags temporal and scheduling words—references to intervals, days/weeks/months, first/next occurrences, and other time‐related expressions.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     هذا
    -0.07
     topology
    -0.07
     prune
    -0.07
     wipes
    -0.07
     setzen
    -0.07
    caps
    -0.06
    _write
    -0.06
     rivers
    -0.06
     occur
    -0.06
     Scots
    -0.06
    POSITIVE LOGITS
    -China
    0.07
     Forum
    0.07
    FirstResponder
    0.07
    	Description
    0.06
     ProgressDialog
    0.06
    >')↵
    0.06
    中國
    0.06
    ía
    0.06
     Florida
    0.06
    quipment
    0.06
    Act Density 0.196%

    No Known Activations