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

    Neuronpedia

    INDEX
    Explanations

    font size and style

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Marine
    0.40
    blem
    0.38
    ¿
    0.38
    自有
    0.38
    ibet
    0.37
    ूला
    0.37
    šen
    0.37
     preoccupied
    0.37
    waitKey
    0.36
    天
    0.36
    POSITIVE LOGITS
    =".$
    0.47
     nuns
    0.45
     सर्दियों
    0.42
     feature
    0.40
     flourishing
    0.40
     lig
    0.40
     numerals
    0.38
     contextual
    0.38
    เชสเตอร์
    0.38
     sumar
    0.38
    Act Density 0.003%

    No Known Activations