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

    Neuronpedia

    INDEX
    Explanations

    version of the

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     parallels
    0.42
     permanece
    0.39
     Neue
    0.38
    Todas
    0.38
    ieth
    0.38
    dependence
    0.37
    Dieses
    0.37
     त्यांच्या
    0.37
    ഒരു
    0.36
     vineyards
    0.36
    POSITIVE LOGITS
     version
    0.50
     classic
    0.50
     версия
    0.46
     версию
    0.45
     기존
    0.45
     обы
    0.44
    经典的
    0.43
     classica
    0.43
     versie
    0.43
     classique
    0.41
    Act Density 0.467%

    No Known Activations