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

    Neuronpedia

    INDEX
    Explanations

    llama, LLMs, locally

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Carrie
    0.44
    Con
    0.38
    Coast
    0.38
    Double
    0.38
    𒋗
    0.38
    طنين
    0.37
     Carrie
    0.37
     বাড়
    0.37
    Tissue
    0.37
    ﮐ
    0.37
    POSITIVE LOGITS
     prothorax
    0.39
    odeficiency
    0.39
    কমার
    0.38
    инг
    0.37
    prits
    0.37
    maket
    0.37
    saver
    0.37
     skrz
    0.36
     brook
    0.36
    ედერ
    0.36
    Act Density 0.000%

    No Known Activations