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

    Neuronpedia

    INDEX
    Explanations

    Code and networking

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     друга
    -0.07
     Conse
    -0.06
    уста
    -0.06
     ml
    -0.06
    	port
    -0.06
    _boost
    -0.06
     Florence
    -0.06
    гу
    -0.05
    	io
    -0.05
    окрем
    -0.05
    POSITIVE LOGITS
    (firstName
    0.08
    кові
    0.07
    بط
    0.07
     accom
    0.07
    .copyOf
    0.06
    半
    0.06
     Invalid
    0.06
    /************************************************************************************************
    0.06
    .Substring
    0.06
    anny
    0.06
    Act Density 0.000%

    No Known Activations