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

    Neuronpedia

    INDEX
    Explanations

    quarters peripherals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     milling
    0.37
    astotal
    0.37
     glaz
    0.36
     kıs
    0.36
    ালার
    0.35
     aromas
    0.35
     pitanje
    0.35
     Kont
    0.35
     প্রশ্ন
    0.35
     tekst
    0.34
    POSITIVE LOGITS
    айл
    0.39
    ilina
    0.38
    ેચ્છ
    0.38
    expr
    0.38
    ζ
    0.36
     определенных
    0.36
    Apparently
    0.34
    Hydrogen
    0.34
     depressed
    0.34
     సాధారణ
    0.34
    Act Density 0.001%

    No Known Activations