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

    Neuronpedia

    INDEX
    Explanations

    collections and related concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     hitherto
    0.48
    ODBA
    0.47
     valuation
    0.46
     aforementioned
    0.44
     trifling
    0.44
     endangering
    0.43
     unset
    0.43
     unscathed
    0.43
     postulated
    0.43
     espec
    0.43
    POSITIVE LOGITS
     között
    0.49
    кая
    0.46
     разные
    0.45
     коллек
    0.45
    Stacks
    0.45
     коллекции
    0.45
    фи
    0.45
     собрать
    0.44
    жды
    0.44
    collected
    0.44
    Act Density 0.001%

    No Known Activations