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

    Neuronpedia

    INDEX
    Explanations

    depends on factors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ängel
    0.41
    heel
    0.39
     Max
    0.37
     Voit
    0.37
    ånd
    0.36
    regul
    0.35
     কাছে
    0.35
    űr
    0.35
    åk
    0.34
     Haaland
    0.34
    POSITIVE LOGITS
     disbelief
    0.41
     therefore
    0.41
     actually
    0.38
     ಎಂಬುದ
    0.38
     connotations
    0.38
     philosophies
    0.37
     mores
    0.37
     transcripts
    0.36
     arguably
    0.36
     পারেনা
    0.35
    Act Density 0.001%

    No Known Activations