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

    Neuronpedia

    INDEX
    Explanations

    code snippets and multilingual

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     PTS
    -0.06
     Nashville
    -0.06
     doivent
    -0.06
    ريكية
    -0.06
    桑
    -0.06
    	mv
    -0.06
     sede
    -0.06
     Dit
    -0.06
    лені
    -0.06
    etroit
    -0.06
    POSITIVE LOGITS
    arser
    0.07
     Obesity
    0.07
    Understanding
    0.07
    ольз
    0.06
    SELECT
    0.06
    calculator
    0.06
    τι
    0.06
    [right
    0.06
     incub
    0.06
     Ξ
    0.06
    Act Density 0.008%

    No Known Activations