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

    Neuronpedia

    INDEX
    Explanations

    LLM-Adapters framework tool integration

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ⬯
    0.45
    蟶
    0.41
    ্টে
    0.41
     못한
    0.40
    CloseOperation
    0.40
    اونلو
    0.40
    ຫານ
    0.39
    寅
    0.39
     Winners
    0.38
    नाल्ड
    0.38
    POSITIVE LOGITS
    rates
    0.42
    ky
    0.42
    ac
    0.42
    des
    0.41
    ide
    0.41
    if
    0.40
    ge
    0.39
     et
    0.39
    Ма
    0.39
    ro
    0.39
    Act Density 0.000%

    No Known Activations