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

    Neuronpedia

    INDEX
    Explanations

    g

    np_max-act · gemini-2.0-flash

    The neuron activates on numeric measurement units (e.g. “g,” “µg,” and similar unit tokens) in quantitative data.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    passed
    -0.07
    еви
    -0.07
    OLUMN
    -0.06
     LSM
    -0.06
    tener
    -0.06
    _supply
    -0.06
    .Run
    -0.06
    ської
    -0.06
    ColumnInfo
    -0.06
    .AnchorStyles
    -0.06
    POSITIVE LOGITS
    报名
    0.07
    .tb
    0.07
     lays
    0.06
    iming
    0.06
    ,’
    0.06
     dps
    0.06
     shape
    0.06
    	alert
    0.06
    _beta
    0.06
     careers
    0.06
    Act Density 0.005%

    No Known Activations