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

    Neuronpedia

    INDEX
    Explanations

    speaker reporting speech

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ఏర్ప
    0.40
     يتم
    0.37
    他们
    0.37
     hệ
    0.36
    rated
    0.36
    利用
    0.36
    ranked
    0.36
     Systems
    0.36
    系统
    0.35
    精度
    0.35
    POSITIVE LOGITS
     says
    0.49
    。
    0.40
     racconta
    0.40
     বলেন
    0.40
     said
    0.39
     कहा
    0.39
     wrote
    0.39
    说道
    0.39
    ".
    0.38
     berkata
    0.38
    Act Density 0.007%

    No Known Activations