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

    Neuronpedia

    INDEX
    Explanations

    Quotation marks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    casting
    -0.08
    OPSIS
    -0.08
    Scaling
    -0.08
     prohibited
    -0.08
     нел
    -0.08
     چیست
    -0.08
     numerator
    -0.08
     propor
    -0.08
     procrast
    -0.08
     принес
    -0.08
    POSITIVE LOGITS
    駅
    0.12
    机场
    0.11
     airports
    0.11
     станции
    0.11
     subway
    0.10
     Flughafen
    0.10
     Airport
    0.10
     airport
    0.10
     railway
    0.10
     stations
    0.10
    Act Density 0.020%

    No Known Activations