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

    Neuronpedia

    INDEX
    Explanations

    code imports or definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     使っ
    0.63
     まず
    0.63
     −/−
    0.59
     thì
    0.58
    బ్బు
    0.58
    និច
    0.58
     suppuration
    0.58
     Vì
    0.57
     těch
    0.57
     Öncelikle
    0.57
    POSITIVE LOGITS
    ↵↵
    0.55
    a
    0.45
    、
    0.43
    Department
    0.43
    {
    0.42
      
    0.41
    Project
    0.41
    <0x0D>
    0.40
    2
    0.39
            
    0.39
    Act Density 0.268%

    No Known Activations