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

    Neuronpedia

    INDEX
    Explanations

    special characters and code snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    +,
    0.43
    tuned
    0.42
    homework
    0.41
    u
    0.40
    II
    0.39
     titan
    0.39
     minivan
    0.39
    ,
    0.39
    while
    0.39
    total
    0.38
    POSITIVE LOGITS
    ﺮ
    0.45
     πρώ
    0.43
    璈
    0.43
     రే
    0.42
    𝚋
    0.42
    फॉर्म
    0.40
     ظِلِّ
    0.40
    竑
    0.40
    ້ງ
    0.40
    ผสม
    0.40
    Act Density 0.001%

    No Known Activations