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

    Neuronpedia

    INDEX
    Explanations

    require

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     posX
    -0.07
     sefer
    -0.06
     scorn
    -0.06
    сон
    -0.06
    	Spring
    -0.06
    言葉
    -0.06
     Hel
    -0.06
    بول
    -0.06
    	HX
    -0.06
    �
    -0.06
    POSITIVE LOGITS
    reference
    0.07
    ./(
    0.06
     requirement
    0.06
    pointer
    0.06
     Requests
    0.06
    _articles
    0.06
    access
    0.06
    (directory
    0.06
     candle
    0.06
     Convenient
    0.06
    Act Density 0.001%

    No Known Activations