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

    Neuronpedia

    INDEX
    Explanations

    like, for example, for

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Border
    0.35
     gång
    0.35
     aix
    0.35
     cps
    0.35
     Emotions
    0.34
     border
    0.33
     feminine
    0.33
     emotion
    0.33
     glass
    0.32
     EXPRESS
    0.32
    POSITIVE LOGITS
    某种
    0.64
    blah
    0.59
     Misalnya
    0.59
     например
    0.59
     مثلا
    0.59
    ispielsweise
    0.57
     bijvoorbeeld
    0.57
     misalnya
    0.57
     beispielsweise
    0.57
    某个
    0.57
    Act Density 0.300%

    No Known Activations