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

    Neuronpedia

    INDEX
    Explanations

    for structured lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     İn
    0.47
     BasicContainer
    0.46
     或者
    0.46
     安全
    0.45
     किस्मत
    0.44
     Tide
    0.44
     ed
    0.43
    ted
    0.43
     Đá
    0.43
    馇
    0.43
    POSITIVE LOGITS
    られている
    0.50
    율
    0.49
     localizada
    0.49
    اة
    0.47
     disponibil
    0.47
     ventaja
    0.46
    ية
    0.46
    أ
    0.45
    롬
    0.45
    лой
    0.44
    Act Density 0.001%

    No Known Activations