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

    Neuronpedia

    INDEX
    Explanations

    specific items or conditions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    לי
    0.46
     ребята
    0.45
     управление
    0.45
     управління
    0.45
    還元
    0.44
    組み立て
    0.43
     wacky
    0.43
    たちの
    0.42
     полити
    0.42
     управления
    0.42
    POSITIVE LOGITS
     melakukannya
    0.53
     seldom
    0.46
     thereof
    0.46
     quelquefois
    0.45
     potrebbe
    0.45
     stvarn
    0.43
     vutto
    0.42
     singoli
    0.42
     rather
    0.41
     even
    0.39
    Act Density 0.118%

    No Known Activations