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

    Neuronpedia

    INDEX
    Explanations

    key elements or aspects

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     преимуще
    0.35
    endenza
    0.32
    不知道
    0.32
     prawo
    0.32
    arantee
    0.32
     beneficio
    0.32
     Vorteil
    0.32
     Hinweis
    0.31
    Joke
    0.31
    iculty
    0.31
    POSITIVE LOGITS
     elements
    1.30
     considerations
    1.23
     aspects
    1.16
     points
    1.13
     areas
    1.13
     éléments
    1.09
     elementos
    1.05
    elements
    1.04
     things
    1.03
    areas
    0.98
    Act Density 0.627%

    No Known Activations