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

    Neuronpedia

    INDEX
    Explanations

    HTML closing tags and elements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     fixation
    0.45
    ARCHIVO
    0.41
    elevationMap
    0.40
     sorption
    0.40
     powerAll
    0.40
    BeginInit
    0.40
    क्षे
    0.39
    丟
    0.39
    товано
    0.39
     स्मिथ
    0.38
    POSITIVE LOGITS
     </
    0.80
    </
    0.76
    </table>
    0.57
    ></
    0.56
     "</
    0.54
    [/
    0.54
    .</
    0.52
     [/
    0.52
    !</
    0.49
     />
    0.49
    Act Density 0.008%

    No Known Activations