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

    Neuronpedia

    INDEX
    Explanations

    page numbers references

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     вихов
    -0.07
    )s
    -0.07
    徐
    -0.07
     columnHeader
    -0.07
    chartInstance
    -0.07
     рок
    -0.07
    狐
    -0.06
    _flg
    -0.06
     Nunes
    -0.06
    isempty
    -0.06
    POSITIVE LOGITS
     instancia
    0.07
    -au
    0.06
    	DEBUG
    0.06
     mysql
    0.06
     Researchers
    0.06
    ICIAL
    0.06
    ANGED
    0.06
    kar
    0.06
    Steam
    0.06
     Gin
    0.06
    Act Density 0.006%

    No Known Activations