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

    Neuronpedia

    INDEX
    Explanations

    defines meaning

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ృతి
    0.38
    水分
    0.38
    чества
    0.38
    тена
    0.37
    විත
    0.35
     bittern
    0.35
    }^{+}+\
    0.35
     посредством
    0.34
    文化的
    0.34
     outweigh
    0.34
    POSITIVE LOGITS
     indicates
    0.77
     denotes
    0.68
     để
    0.68
     indicating
    0.66
     signifies
    0.59
     Indicates
    0.59
     denoting
    0.59
     oznacza
    0.57
     表示
    0.56
     signifying
    0.56
    Act Density 0.481%

    No Known Activations