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

    Neuronpedia

    INDEX
    Explanations

    glossary and terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     methodological
    0.46
     letzte
    0.46
    𝗢
    0.46
    lastval
    0.45
     popraw
    0.44
     последнее
    0.43
    nachweise
    0.43
     ፓ
    0.43
     לא
    0.42
     puntual
    0.42
    POSITIVE LOGITS
     glossary
    0.60
    Gloss
    0.58
     Glossary
    0.56
    gloss
    0.54
     Understanding
    0.48
     gloss
    0.46
    terms
    0.45
     dictionary
    0.45
     understanding
    0.44
     Gloss
    0.44
    Act Density 0.006%

    No Known Activations