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

    Neuronpedia

    INDEX
    Explanations

    * then text

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     bytes
    0.30
     sequences
    0.29
     vertices
    0.28
     polynomials
    0.28
     columns
    0.28
     $(
    0.28
     glyph
    0.27
     perturbation
    0.27
     vertex
    0.27
     polynomial
    0.27
    POSITIVE LOGITS
     Governo
    0.31
    ările
    0.29
    媺
    0.28
     сотрудни
    0.28
    Источник
    0.27
    Votre
    0.27
    Ро
    0.27
     Fransiya
    0.27
     incrível
    0.26
    Além
    0.26
    Act Density 0.453%

    No Known Activations