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

    Neuronpedia

    INDEX
    Explanations

    commands and rules

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     sillons
    0.56
    0.46
     खुदाई
    0.45
     ವಿಧಾನ
    0.44
    ード
    0.44
    ก็ตาม
    0.44
    TreeNavigator
    0.43
    zeniem
    0.43
     bloques
    0.43
     niches
    0.42
    POSITIVE LOGITS
     as
    0.49
    verband
    0.45
     personality
    0.42
     player
    0.42
     a
    0.41
     fabricated
    0.41
     posta
    0.40
     paint
    0.40
     homegrown
    0.40
     weather
    0.39
    Act Density 0.004%

    No Known Activations