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

    Neuronpedia

    INDEX
    Explanations

    foundational

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    1.50
    ли
    1.10
    ле
    1.06
     labored
    0.99
    會在
    0.99
     Utilize
    0.92
    ğ
    0.92
    會
    0.91
    льзя
    0.91
    ých
    0.91
    POSITIVE LOGITS
    ת
    1.41
     found
    1.36
     be
    1.34
    ک
    1.34
    st
    1.26
    found
    1.22
    י
    1.21
    ה
    1.20
    কে
    1.19
    ก
    1.19
    Act Density 0.020%

    No Known Activations