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

    Neuronpedia

    INDEX
    Explanations

    php code snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    اً
    3.50
    ときに
    2.62
    tion
    2.59
    л
    2.53
    jenigen
    2.52
    ১৮
    2.52
    น่า
    2.51
    ojen
    2.49
    terbury
    2.47
    ことができる
    2.45
    POSITIVE LOGITS
    ई
    2.77
    2.71
    ische
    2.59
    ज
    2.48
    MyAdmin
    2.43
    ay
    2.42
    potion
    2.40
    ouk
    2.40
    irk
    2.40
     صلى
    2.39
    Act Density 0.039%

    No Known Activations