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

    Neuronpedia

    INDEX
    Explanations

    acronyms and abbreviations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    opposition
    0.42
     विरोधी
    0.42
     nailing
    0.39
    बै
    0.39
    状态
    0.38
    hop
    0.38
    过去的
    0.38
    0.38
    oppositions
    0.37
     kwest
    0.37
    POSITIVE LOGITS
     Erd
    0.45
     গান্ধ
    0.38
     Tân
    0.37
     deren
    0.36
     광고
    0.36
     본
    0.35
     (°
    0.35
    ৌজ
    0.35
    ควบคุม
    0.35
     항
    0.35
    Act Density 0.001%

    No Known Activations