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

    Neuronpedia

    INDEX
    Explanations

    C++ string streams

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     justiça
    0.42
     resp
    0.38
     Milner
    0.38
     расположен
    0.38
    quina
    0.38
     kry
    0.37
     крити
    0.37
     ক্রমবর্ধমান
    0.37
     ENC
    0.37
     chris
    0.36
    POSITIVE LOGITS
    பா
    0.42
    aters
    0.39
    Entries
    0.38
    uc
    0.38
    bd
    0.38
    アウト
    0.36
    Rx
    0.36
    ່ວ
    0.36
    人に
    0.36
    ić
    0.35
    Act Density 0.001%

    No Known Activations