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

    Neuronpedia

    INDEX
    Explanations

    you can see

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    an
    0.57
    AN
    0.50
    ان
    0.46
     বহ
    0.45
    luster
    0.43
    aver
    0.43
     alle
    0.43
    ead
    0.42
    glomer
    0.42
    aktan
    0.42
    POSITIVE LOGITS
     Chủ
    0.49
    aphylococcus
    0.46
    θεί
    0.45
     docked
    0.44
     Mạnh
    0.44
     nourished
    0.44
    łoż
    0.43
     Morocco
    0.42
     Maroc
    0.42
    줍니다
    0.42
    Act Density 0.008%

    No Known Activations