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

    Neuronpedia

    INDEX
    Explanations

    invalid JSON or structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AppSettings
    0.45
     enquête
    0.44
    榞
    0.43
     然後
    0.42
     നടന്ന
    0.41
     प्रेरणा
    0.41
    ঞ্চলের
    0.41
    IsEnabled
    0.41
    SearchResults
    0.40
     ഞാന്‍
    0.40
    POSITIVE LOGITS
    ima
    0.40
    ite
    0.40
     mundane
    0.39
    amer
    0.38
    зи
    0.37
    lett
    0.37
     solucionar
    0.36
     matemat
    0.35
    物理
    0.35
    amera
    0.35
    Act Density 0.001%

    No Known Activations