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

    Neuronpedia

    INDEX
    Explanations

    Numbers and positions

    np_max-act · gemini-2.0-flash

    The neuron detects specific schedule or timing details, especially numerical expressions of days and times.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    .ret
    -0.07
    esh
    -0.07
    erchant
    -0.06
    ART
    -0.06
     skip
    -0.06
    _permission
    -0.06
    Statistic
    -0.06
    .Utility
    -0.06
    _CACHE
    -0.06
    ScrollIndicator
    -0.06
    POSITIVE LOGITS
    ns
    0.06
     qua
    0.06
    	Config
    0.06
    -yyyy
    0.06
     completing
    0.06
    �建
    0.05
    _region
    0.05
    _inv
    0.05
    ㅎ
    0.05
    (CONFIG
    0.05
    Act Density 0.110%

    No Known Activations