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

    Neuronpedia

    INDEX
    Explanations

    explain your reasoning

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ing
    1.03
    ة
    0.97
    ron
    0.94
    ed
    0.93
    ite
    0.92
    a
    0.90
    ynchron
    0.89
    ên
    0.88
     the
    0.88
    ate
    0.87
    POSITIVE LOGITS
    ऑक्साइड
    0.98
    ร้าง
    0.98
     obtenus
    0.95
     очень
    0.93
    琬
    0.93
     perin
    0.92
    퐶
    0.90
    Ꮺ
    0.90
     област
    0.89
    medallas
    0.89
    Act Density 0.000%

    No Known Activations