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

    Neuronpedia

    INDEX
    Explanations

    external items or concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    "
    1.23
     I
    1.23
    ↵
    1.10
    -
    1.06
    大
    1.00
     来
    0.99
    {
    0.98
    ياء
    0.98
     Alamos
    0.98
    }"
    0.96
    POSITIVE LOGITS
    ק
    1.45
    ر
    1.34
    uk
    1.32
    ل
    1.22
    க
    1.22
    ม
    1.21
    б
    1.20
    я
    1.16
     external
    1.15
    ल
    1.14
    Act Density 0.009%

    No Known Activations