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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    囗
    0.40
    肐
    0.37
    郯
    0.37
    ⺈
    0.36
    𒌆
    0.36
     гуляць
    0.35
     Гуляць
    0.34
    𒀸
    0.34
    ית
    0.34
    ಶ್ಚ
    0.33
    POSITIVE LOGITS
    if
    0.42
    ve
    0.39
    num
    0.38
    try
    0.38
     this
    0.36
     if
    0.36
     it
    0.36
      
    0.34
    res
    0.34
    return
    0.33
    Act Density 0.189%

    No Known Activations