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

    Neuronpedia

    INDEX
    Explanations

    adding a section

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Edition
    0.39
     edition
    0.38
     Arbe
    0.38
    Within
    0.38
     edição
    0.38
    ovaná
    0.37
     incluido
    0.37
    oreo
    0.37
     지난해
    0.37
    *:
    0.37
    POSITIVE LOGITS
     critters
    0.42
     crit
    0.39
     generell
    0.39
     celles
    0.39
     khusus
    0.38
    प्लेक्स
    0.38
    푅
    0.38
     consacré
    0.38
    䬲
    0.38
     devoted
    0.37
    Act Density 0.042%

    No Known Activations