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

    Neuronpedia

    INDEX
    Explanations

    beginnings of code files

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     subordination
    0.34
     physiologic
    0.31
     necrosis
    0.30
     demur
    0.30
     discontinuity
    0.30
     solubilities
    0.30
     trypsin
    0.29
     isoform
    0.29
    tAux
    0.29
     perfused
    0.29
    POSITIVE LOGITS
     Hello
    0.37
     Superhero
    0.32
    Hello
    0.31
     Mini
    0.31
    簡単な
    0.30
    ã
    0.30
     만들기
    0.30
     Ninja
    0.30
     Simple
    0.29
     Pokemon
    0.29
    Act Density 0.721%

    No Known Activations