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

    Neuronpedia

    INDEX
    Explanations

    technical terms

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Avl
    0.71
    рование
    0.71
    ্ঠ
    0.68
    ួរ
    0.67
     tolerable
    0.67
     রানী
    0.67
     groove
    0.66
     ওয়াস
    0.64
    ಲಾಯಿತು
    0.63
     García
    0.62
    POSITIVE LOGITS
    塵
    0.70
    mlich
    0.70
    dom
    0.70
    尘
    0.69
     રોજ
    0.69
    Collider
    0.67
    镑
    0.67
    溜
    0.67
    ন্ডি
    0.67
     Bloomberg
    0.66
    Act Density 0.066%

    No Known Activations