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

    Neuronpedia

    INDEX
    Explanations

    preceding specific entities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Estamos
    0.35
    วัสดี
    0.34
     españa
    0.34
     simonsen
    0.34
     italia
    0.33
     organizações
    0.33
    Diese
    0.33
    Questo
    0.33
     pedro
    0.33
     entidades
    0.32
    POSITIVE LOGITS
     the
    0.39
    it
    0.32
      
    0.32
     a
    0.32
    0.32
     S
    0.32
     “
    0.32
     it
    0.30
     (
    0.30
     and
    0.29
    Act Density 0.282%

    No Known Activations