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

    Neuronpedia

    INDEX
    Explanations

    _

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    “我
    -0.07
     cityName
    -0.06
    -0.06
    (Get
    -0.06
     snowy
    -0.06
    '])
↵
    -0.06
    	xml
    -0.06
    .dirty
    -0.06
     ду
    -0.06
    ुरस
    -0.06
    POSITIVE LOGITS
    crow
    0.07
     Ebola
    0.07
    止
    0.06
     bons
    0.06
    .weight
    0.06
    aday
    0.06
     Jazeera
    0.06
    .backends
    0.06
    weights
    0.06
    JECTED
    0.06
    Act Density 0.098%

    No Known Activations