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

    Neuronpedia

    INDEX
    Explanations

    Code/Technical snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     heaps
    -0.07
    ebin
    -0.06
    806
    -0.06
     Gunn
    -0.06
    ioni
    -0.06
     objs
    -0.06
     fout
    -0.06
    	router
    -0.06
     shifts
    -0.06
    Please
    -0.06
    POSITIVE LOGITS
     콜
    0.07
    致
    0.07
    (scores
    0.07
     отри
    0.07
    رى
    0.06
    _MAKE
    0.06
    override
    0.06
    (cl
    0.06
     мест
    0.06
     bers
    0.06
    Act Density 0.037%

    No Known Activations