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

    Neuronpedia

    INDEX
    Explanations

    recommend

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     limit
    -0.07
    061
    -0.07
     hour
    -0.06
     blue
    -0.06
    .year
    -0.06
     passport
    -0.06
     Engel
    -0.06
     wagon
    -0.06
     baking
    -0.06
    our
    -0.06
    POSITIVE LOGITS
    	RuntimeObject
    0.07
     Schwar
    0.06
     {↵↵↵↵
    0.06
     Společ
    0.06
     tảng
    0.06
    .newLine
    0.06
    olt
    0.06
    stand
    0.06
     České
    0.06
     setId
    0.06
    Act Density 0.056%

    No Known Activations