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

    Neuronpedia

    INDEX
    Explanations

    Testament

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    h
    1.09
    我
    0.80
    被
    0.78
    <0xE7>
    0.77
    k
    0.77
    地
    0.77
    ва
    0.76
     Sit
    0.76
    把
    0.75
     Chat
    0.75
    POSITIVE LOGITS
     летом
    1.11
    Lavender
    1.05
    ાદ
    1.02
    Palindrome
    1.01
    nsec
    0.99
     ग्रेटर
    0.98
    speople
    0.98
    ூர்
    0.96
     sultry
    0.96
     simonsen
    0.96
    Act Density 0.001%

    No Known Activations