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

    Neuronpedia

    INDEX
    Explanations

    increase and decrease

    np_max-act · gemini-2.0-flash

    The neuron activates on words and phrases that describe experimental outcomes or measured changes (e.g. increased, decreased, ameliorated, accumulation, improvement).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    otypes
    -0.07
    egade
    -0.06
     pandemic
    -0.06
    osal
    -0.06
     sciences
    -0.06
     ended
    -0.06
    _tgt
    -0.06
     действительно
    -0.06
    isease
    -0.06
    Netflix
    -0.06
    POSITIVE LOGITS
    	REG
    0.08
     comboBox
    0.07
    ThanOrEqualTo
    0.06
     Deployment
    0.06
    	dfs
    0.06
     sola
    0.06
    준
    0.06
    少し
    0.06
     şehir
    0.06
     hPa
    0.06
    Act Density 0.034%

    No Known Activations