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

    Neuronpedia

    INDEX
    Explanations

    defining characteristics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    都需要
    0.44
    sama
    0.43
     Cinnamon
    0.43
    😂
    0.42
    bours
    0.41
     इच्छा
    0.41
     Dua
    0.40
    ിലേ
    0.40
    ibouti
    0.40
     Executors
    0.39
    POSITIVE LOGITS
     легко
    0.49
    мі
    0.47
    гі
    0.45
     métal
    0.44
    мін
    0.44
    Grouping
    0.43
    Identify
    0.42
     компакт
    0.41
     группа
    0.40
    жер
    0.40
    Act Density 0.031%

    No Known Activations