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

    Neuronpedia

    INDEX
    Explanations

    abstract concepts and descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     the
    0.60
     be
    0.42
    1
    0.41
    )
    0.41
     to
    0.41
     for
    0.40
     or
    0.40
     that
    0.38
     User
    0.38
     can
    0.38
    POSITIVE LOGITS
     meriye
    0.45
     ແລະ
    0.42
     револю
    0.41
    ４
    0.41
    ۵
    0.41
     alegría
    0.40
     искусства
    0.40
    ៥
    0.40
     REGIUNI
    0.40
    vykor
    0.40
    Act Density 0.072%

    No Known Activations