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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Knight
    -0.07
    ZONE
    -0.07
     Vk
    -0.07
    	protected
    -0.07
    moon
    -0.07
    jdk
    -0.07
     discussed
    -0.07
    Narr
    -0.07
     mük
    -0.07
    �
    -0.07
    POSITIVE LOGITS
     upbeat
    0.06
    аров
    0.06
    履
    0.06
    <Employee
    0.06
     Academ
    0.05
    iov
    0.05
    ictory
    0.05
     obsess
    0.05
    (Double
    0.05
    чески
    0.05
    Act Density 0.001%

    No Known Activations