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

    Neuronpedia

    INDEX
    Explanations

    counting or no

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    notes
    0.47
     notes
    0.44
    ionic
    0.43
    Markdown
    0.41
     escalation
    0.41
    už
    0.40
     accounts
    0.39
    Share
    0.39
    笔记
    0.39
    ysi
    0.39
    POSITIVE LOGITS
     ninguna
    0.50
     никакого
    0.45
     aucun
    0.44
     Directly
    0.43
     geen
    0.43
     никаких
    0.42
     उनसे
    0.41
     nenhum
    0.40
     nenhuma
    0.40
     Avoid
    0.39
    Act Density 0.000%

    No Known Activations