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

    Neuronpedia

    INDEX
    Explanations

    indicative of potential issues

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Answer
    0.50
    A
    0.48
    Section
    0.48
    Namara
    0.48
    Address
    0.46
    Assume
    0.46
    ProjectId
    0.46
    Ky
    0.46
    Pose
    0.45
    :
    0.45
    POSITIVE LOGITS
     文件
    0.50
    iros
    0.46
     Sedangkan
    0.46
     אחר
    0.46
     不是
    0.43
     工作
    0.43
     ـ
    0.42
    ﺗ
    0.42
    鏤
    0.42
    ioxid
    0.41
    Act Density 0.001%

    No Known Activations