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

    Neuronpedia

    INDEX
    Explanations

    data privacy

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Called
    0.49
    ມີ
    0.49
    称为
    0.45
    кисло
    0.44
     называ
    0.44
     বিষয়ে
    0.43
    hesized
    0.43
    绺
    0.43
     تعریف
    0.42
    WED
    0.42
    POSITIVE LOGITS
     grund
    0.50
     privaten
    0.48
     absences
    0.48
     absolut
    0.47
     EXE
    0.47
     absol
    0.47
     funkt
    0.47
     limo
    0.47
     EMA
    0.46
     resultat
    0.46
    Act Density 0.004%

    No Known Activations