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

    Neuronpedia

    INDEX
    Explanations

    Verd

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	header
    -0.07
    batim
    -0.07
     Colonial
    -0.06
    Harry
    -0.06
    WebpackPlugin
    -0.06
     後
    -0.06
    socket
    -0.06
    TOKEN
    -0.06
    ाखण
    -0.06
     lenses
    -0.06
    POSITIVE LOGITS
    legend
    0.08
    RD
    0.08
     زیرا
    0.07
    ($(
    0.07
    	 
↵
    0.07
    _Success
    0.07
     юрид
    0.07
    UBL
    0.07
     Verd
    0.07
    ERC
    0.07
    Act Density 0.005%

    No Known Activations