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

    Neuronpedia

    INDEX
    Explanations

    analyze structures and relationships

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    㭉
    0.52
    nnc
    0.48
     น้อย
    0.46
     ആഘോഷ
    0.46
    candles
    0.46
     对象
    0.45
    initializer
    0.45
    AdType
    0.45
    devkit
    0.45
     EDITION
    0.45
    POSITIVE LOGITS
     =
    0.52
     to
    0.50
     >
    0.47
     una
    0.47
     comando
    0.46
    ками
    0.46
    मान
    0.46
    E
    0.46
    اي
    0.45
     ₹
    0.45
    Act Density 0.000%

    No Known Activations