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

    Neuronpedia

    INDEX
    Explanations

    Physical Review journal references

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ศ์
    0.46
     affront
    0.43
     ওয়াল
    0.41
     inserted
    0.40
     treason
    0.40
     ガラス
    0.40
     чу
    0.40
    ុម
    0.39
    arged
    0.39
     galvanized
    0.39
    POSITIVE LOGITS
    Pr
    0.46
     Pr
    0.44
    log
    0.41
    ارب
    0.41
     स्थिरता
    0.39
    运行
    0.39
    日志
    0.39
    Running
    0.39
    循环
    0.38
     log
    0.37
    Act Density 0.000%

    No Known Activations