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

    Neuronpedia

    INDEX
    Explanations

    RLHF

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    躊
    0.43
    ВИ
    0.42
    予測
    0.39
    oulis
    0.38
    veli
    0.38
    atho
    0.37
    resi
    0.37
    avamo
    0.36
    insi
    0.36
     nay
    0.35
    POSITIVE LOGITS
     linha
    0.40
     slee
    0.38
     الخارج
    0.38
    とおり
    0.37
     desech
    0.37
     setLayout
    0.37
     有
    0.37
     दिसत
    0.36
     React
    0.36
    ताब
    0.36
    Act Density 0.002%

    No Known Activations