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

    Neuronpedia

    INDEX
    Explanations

    sequence transduction tasks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Type
    0.45
     introdu
    0.43
    Techn
    0.42
    天空
    0.42
    Control
    0.41
    Tek
    0.41
     discussions
    0.40
     Introduction
    0.40
     overkill
    0.39
    Dark
    0.39
    POSITIVE LOGITS
    ِی
    0.51
    жное
    0.50
    жен
    0.49
    ленных
    0.49
    Укупно
    0.46
     schop
    0.46
     système
    0.45
    ное
    0.44
    ých
    0.44
    नाची
    0.44
    Act Density 0.003%

    No Known Activations